© 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. 5-GEMMASCOPE-RES-16K
    11. 13912
    Prev
    Next
    INDEX
    Explanations

    specific references to user-related information and technical document structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     חיצוניים
    -0.78
     BoxDecoration
    -0.74
    IntoConstraints
    -0.73
    pushFollow
    -0.71
     الرياضيه
    -0.71
    principalColumn
    -0.65
     Numerade
    -0.64
    bní
    -0.64
    Geplaatst
    -0.63
    tificate
    -0.63
    POSITIVE LOGITS
    Rhestr
    0.77
    </em>
    0.73
    </i>
    0.69
     Städten
    0.54
    iacute
    0.54
     kasarigan
    0.54
    Véxase
    0.54
    DebuggerNonUser
    0.50
     chil
    0.48
     Vib
    0.46
    Activations Density 0.291%

    No Known Activations