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

    Neuronpedia

    APICircuit 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 - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1765
    Prev
    Next
    INDEX
    Explanations

    elements related to data structures and programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     esternos
    -0.70
    脚注の使い方
    -0.66
    RenderAtEndOf
    -0.54
     BoxFit
    -0.54
    杓
    -0.53
    handeling
    -0.52
    verif
    -0.52
     <=",
    -0.51
    嘧
    -0.50
     deal
    -0.49
    POSITIVE LOGITS
    TextBoxColumn
    1.04
    DeleteBehavior
    0.60
    DataPropertyName
    0.59
    ISupport
    0.57
     portefeuille
    0.54
     quæ
    0.54
     Púb
    0.53
    alnız
    0.53
    assertIn
    0.52
    hasOwnProperty
    0.51
    Activations Density 0.006%

    No Known Activations