© 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. 15-GEMMASCOPE-RES-16K
    11. 1377
    Prev
    Next
    INDEX
    Explanations

    locations or contexts related to events and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlType
    -0.49
    schrift
    -0.48
     samo
    -0.41
    esprit
    -0.40
    ęty
    -0.38
     AsyncTask
    -0.37
    льт
    -0.37
    ↵
    -0.37
     farsi
    -0.37
    pc
    -0.36
    POSITIVE LOGITS
     للمعارف
    1.10
     Où
    0.96
    RetentionPolicy
    0.93
     Where
    0.89
     ProtoMessage
    0.86
    Where
    0.86
    ніципалі
    0.86
     Places
    0.85
     where
    0.84
    ConstraintMaker
    0.83
    Activations Density 0.156%

    No Known Activations