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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11277
    Prev
    Next
    INDEX
    Explanations

    references to the concept of survival

    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
    DeleteBehavior
    -0.80
    脚注の使い方
    -0.73
    tonode
    -0.69
    MENAFN
    -0.68
     JpaRepository
    -0.65
     للمعارف
    -0.64
    StoreMessageInfo
    -0.64
    findpost
    -0.63
    webElement
    -0.63
    AddTagHelper
    -0.61
    POSITIVE LOGITS
    LookAnd
    0.58
    Sur
    0.56
     rounding
    0.54
     Sur
    0.52
    rog
    0.48
    ROUND
    0.48
    strö
    0.47
     SUR
    0.47
    ValueStyle
    0.46
    ounded
    0.46
    Activations Density 0.156%

    No Known Activations