© 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. 28-GEMMASCOPE-RES-16K
    11. 8026
    Prev
    Next
    INDEX
    Explanations

    elements related to roles and responsibilities within various contexts

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

    Interested people/applicants followed by instructions or requests

    np_acts-logits-general · gemini-2.0-flash

    interested applicants please

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    viato
    -0.32
     sto
    -0.32
     BAT
    -0.32
    裂
    -0.30
     par
    -0.30
    idat
    -0.30
     chẳng
    -0.29
    象
    -0.29
     iss
    -0.28
     por
    -0.28
    POSITIVE LOGITS
     should
    0.99
    should
    0.84
     Should
    0.77
     please
    0.76
     powin
    0.76
     needn
    0.75
    Should
    0.73
    
    0.73
    hould
    0.71
     fhould
    0.71
    Activations Density 0.426%

    No Known Activations