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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 5712
    Prev
    Next
    INDEX
    Explanations

    components related to the importance and role of various processes, factors, and structures in biological and health contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.73
     autorytatywna
    -0.65
    AutoScaleMode
    -0.62
     समीक्षाओं
    -0.58
    dafx
    -0.56
     IEnumerator
    -0.56
     оригіналу
    -0.55
    도록
    -0.54
    WebMethod
    -0.54
    jooq
    -0.54
    POSITIVE LOGITS
     important
    3.28
     crucial
    2.85
    important
    2.84
     vital
    2.71
     Important
    2.69
    Important
    2.55
     essential
    2.55
     critical
    2.35
     importante
    2.30
    重要
    2.30
    Activations Density 1.064%

    No Known Activations