© 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. 5-GEMMASCOPE-RES-16K
    11. 846
    Prev
    Next
    INDEX
    Explanations

    the start of a new content section or paragraph within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     raiſ
    -0.89
    GEBURTSDATUM
    -0.88
     againſt
    -0.88
     becauſe
    -0.87
     uſed
    -0.85
    AutoScaleMode
    -0.83
    aarrggbb
    -0.81
     itſelf
    -0.80
    TypedDataSet
    -0.80
     Perfon
    -0.80
    POSITIVE LOGITS
     I
    0.60
    IMPORTED
    0.57
     the
    0.55
    िन्न
    0.51
     My
    0.51
     nonatomic
    0.51
    enumi
    0.50
    lihatkan
    0.50
    .
    0.50
    keiten
    0.49
    Activations Density 0.026%

    No Known Activations