© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 14629
    Prev
    Next
    INDEX
    Explanations

    modal verbs expressing possibility, necessity, or permission

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    question words that start sentences (Can, Was, Did, Whether, Could, Would, Haven't, Is).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgsConstructor
    -0.45
    ⟭
    -0.43
     """",
    -0.43
    nicks
    -0.43
     emailAlready
    -0.43
    Panamoan
    -0.42
    contentLoaded
    -0.42
    CloseOperation
    -0.42
    erted
    -0.41
     referrerpolicy
    -0.41
    POSITIVE LOGITS
    abestanden
    0.66
     anyone
    0.62
     there
    0.60
     they
    0.59
     anybody
    0.56
     it
    0.55
     we
    0.54
    anyone
    0.50
    Anyone
    0.46
    Anybody
    0.46
    Activations Density 0.404%

    No Known Activations