© 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. 2-GEMMASCOPE-RES-16K
    6. 8278
    Prev
    Next
    INDEX
    Explanations

    references to biological concepts and terms related to biochemistry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedDtor
    -0.48
    /**
    -0.45
     ContentValues
    -0.43
     חיצוניים
    -0.42
     defStyle
    -0.40
     الحره
    -0.39
    räck
    -0.38
    tagHelperRunner
    -0.38
     poveznice
    -0.37
    әрмәләр
    -0.37
    POSITIVE LOGITS
     interpretation
    0.73
    rungsseite
    0.69
    ico
    0.69
     VA
    0.68
     circular
    0.67
     Interpretation
    0.65
     interpretations
    0.65
     bi
    0.64
     interprets
    0.64
     interpreting
    0.63
    Activations Density 0.571%

    No Known Activations