© 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-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 7746
    Prev
    Next
    INDEX
    Explanations

    package and import declarations in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſeveral
    -0.84
     itſelf
    -0.80
     themſelves
    -0.79
     pleaſure
    -0.73
     myſelf
    -0.73
     ſta
    -0.72
     ſtre
    -0.72
     Reſ
    -0.72
     himſelf
    -0.71
     juſ
    -0.71
    POSITIVE LOGITS
    //
    1.23
    package
    1.10
    /**
    0.93
    #
    0.85
    /*
    0.81
     henvisninger
    0.75
     createSlice
    0.73
    PerformLayout
    0.65
    Geplaatst
    0.64
    import
    0.63
    Activations Density 0.171%

    No Known Activations