© 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. 3-GEMMASCOPE-RES-16K
    11. 5806
    Prev
    Next
    INDEX
    Explanations

    the presence of phrases related to legal obligations and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.38
    IUrlHelper
    -0.36
    <eos>
    -0.35
     cous
    -0.35
    乓
    -0.34
     {?}
    -0.32
     AssemblyVersion
    -0.32
    WriteBarrier
    -0.31
     guar
    -0.31
    weightedMode
    -0.31
    POSITIVE LOGITS
    :✨
    0.71
    SharedCtor
    0.61
    팎
    0.54
     mijne
    0.54
    Personensuche
    0.52
     umani
    0.52
     invokingState
    0.51
     zijne
    0.51
    ьажоргаш
    0.50
    heça
    0.50
    Activations Density 1.352%

    No Known Activations