© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 14224
    Prev
    Next
    INDEX
    Explanations

    references to formal reports and inquiries, particularly those related to policing and audits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    formal governmental or institutional reviews, reports, inquiries, and investigations, especially references to named commissions, publication, and recommendations

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    official reports, reviews, and inquiries, particularly government or institutional investigations.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hicles
    -0.45
     Canti
    -0.41
     Belts
    -0.40
    dimin
    -0.39
    Билгалдахарш
    -0.39
    FieldDescriptor
    -0.39
    ContentAsync
    -0.38
     belts
    -0.38
    Skinny
    -0.38
     Dimin
    -0.37
    POSITIVE LOGITS
     investigation
    0.60
     investigations
    0.59
    investigation
    0.58
    調查
    0.56
     report
    0.55
     inquiry
    0.54
     Investigations
    0.52
     commissioned
    0.52
     onderzoek
    0.51
    studies
    0.51
    Activations Density 0.779%

    No Known Activations