Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 14921
    Prev
    Next
    INDEX
    Explanations

    various forms of the verb "to be" and expressions of possibility or hypothetical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     schop
    -0.33
    قال
    -0.32
     dignité
    -0.31
    ❋
    -0.30
    ptid
    -0.29
     câte
    -0.27
    diali
    -0.27
    ')(
    -0.26
     saites
    -0.26
    MessageOf
    -0.26
    POSITIVE LOGITS
     pure
    0.97
     proof
    0.85
    pure
    0.83
     overkill
    0.79
     manna
    0.77
     pura
    0.77
     PURE
    0.77
    ConstraintMaker
    0.76
    AndEndTag
    0.76
     heaven
    0.74
    Activations Density 0.539%

    No Known Activations