© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 14004
    Prev
    Next
    INDEX
    Explanations

    the phrase "mid" indicating conditional probabilities or expectations in statistical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 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
    adaptiveStyles
    -1.13
    HasForeignKey
    -0.91
    forRoot
    -0.86
    LikeLike
    -0.84
    SaveChangesAsync
    -0.74
    globalData
    -0.73
    RenderAtEndOf
    -0.72
    toMatchSnapshot
    -0.72
    RTDA
    -0.71
    ſelves
    -0.71
    POSITIVE LOGITS
     vor
    1.18
     Vor
    0.97
    Vor
    0.84
     ab
    0.77
    vor
    0.73
     ale
    0.70
     aber
    0.68
     но
    0.66
    #!/
    0.65
     ber
    0.55
    Activations Density 0.057%

    No Known Activations