© 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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 39506
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to enumerations and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tanggung
    -0.60
     oby
    -0.52
    Spoljašnje
    -0.51
     обязан
    -0.49
    o
    -0.48
     عال
    -0.48
     crystallized
    -0.48
    <eos>
    -0.48
    rimas
    -0.47
    CDCl
    -0.47
    POSITIVE LOGITS
     öffnungszeiten
    0.92
    QPalette
    0.87
     enum
    0.84
     myſelf
    0.83
     poffible
    0.81
    setViewportView
    0.80
     raiſ
    0.80
     Majefty
    0.80
    ſelves
    0.79
     ErrIntOverflow
    0.79
    Activations Density 0.004%

    No Known Activations