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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 8305
    Prev
    Next
    INDEX
    Explanations

    concepts related to research and its regulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     interface
    -0.38
     egli
    -0.35
    interface
    -0.34
    IVIDUAL
    -0.32
    plain
    -0.31
    立ち
    -0.31
    ništ
    -0.31
    blit
    -0.31
    INTERFACE
    -0.31
     Interface
    -0.31
    POSITIVE LOGITS
    AddTagHelper
    0.78
     INVESTIGATION
    0.67
     investigation
    0.66
    tagHelperRunner
    0.66
     research
    0.65
     Investigation
    0.63
     investigations
    0.63
    Investigation
    0.62
     disambiguazione
    0.61
    investigation
    0.60
    Activations Density 0.171%

    No Known Activations