© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 9864
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and installation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     continúas
    -0.80
    oredCriteria
    -0.76
    MigrationBuilder
    -0.69
    StreetMap
    -0.67
    AutoField
    -0.65
    TagMode
    -0.63
     &___
    -0.63
    ]();
    -0.60
    SourceChecksum
    -0.60
    Morfologia
    -0.60
    POSITIVE LOGITS
    ه‌
    0.61
    دانشنامهٔ
    0.57
     caminhos
    0.54
     clairement
    0.52
    WebVitals
    0.52
     carriera
    0.50
     tóxic
    0.49
     Lieblings
    0.49
     artt
    0.49
     attiv
    0.48
    Activations Density 2.036%

    No Known Activations