© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14662
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hentet
    -0.71
    <unused47>
    -0.69
    <unused79>
    -0.69
    [@BOS@]
    -0.69
    <unused3>
    -0.69
    <unused41>
    -0.68
    <unused51>
    -0.68
    <unused28>
    -0.68
    <unused17>
    -0.68
    <unused23>
    -0.68
    POSITIVE LOGITS
     always
    0.38
     immediately
    0.37
    oneofs
    0.33
     reminded
    0.31
     lembrar
    0.31
     when
    0.31
     sensação
    0.30
     Eisenbahn
    0.30
     évo
    0.30
     remind
    0.29
    Activations Density 0.265%

    No Known Activations