© 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. 24-GEMMASCOPE-RES-16K
    6. 5639
    Prev
    Next
    INDEX
    Explanations

    conversational phrases and indications of thought processes

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

    Follows certain words like "deny" or "admitted"

    np_acts-logits-general · gemini-2.0-flash

    defendants admit or deny

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementXpaths
    -0.90
     CreateTagHelper
    -0.79
    RTGC
    -0.60
    ScopeManager
    -0.59
    SharedCtor
    -0.59
    :✨
    -0.57
    SharedDtor
    -0.57
     appelez
    -0.55
    الحياه
    -0.53
    RTHOOK
    -0.51
    POSITIVE LOGITS
     NSCoder
    0.45
     الحره
    0.45
    ConstraintMaker
    0.43
    [,]
    0.41
    plish
    0.40
    getContentPane
    0.40
     ruinas
    0.39
    Demografie
    0.39
    ãng
    0.39
    󠁣
    0.39
    Activations Density 1.735%

    No Known Activations