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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 13526
    Prev
    Next
    INDEX
    Explanations

    bracketed phrases, references, or citations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setcounter
    -0.58
    ChildScrollView
    -0.56
    setVerticalGroup
    -0.54
    ウンテン
    -0.47
     '/';
    -0.47
    الصفحه
    -0.46
    /');
    -0.46
     CreateTagHelper
    -0.44
     تانيه
    -0.43
     TestBed
    -0.42
    POSITIVE LOGITS
    脚注の使い方
    1.04
    invokeLater
    0.74
    ngdoc
    0.71
    Архівовано
    0.71
    makeConstraints
    0.70
    الدراسه
    0.69
    basicConfig
    0.68
    MigrationBuilder
    0.68
    toHexString
    0.63
    瘍
    0.63
    Activations Density 0.127%

    No Known Activations