© 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. 4-GEMMASCOPE-RES-16K
    11. 3717
    Prev
    Next
    INDEX
    Explanations

    programming and technical terms related to methods and properties

    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
     Mehdi
    -0.52
    őbb
    -0.46
    Luong
    -0.45
    DIPSETTING
    -0.44
     minori
    -0.44
    cerned
    -0.43
     scio
    -0.43
    azul
    -0.42
     Investigaciones
    -0.42
     transcur
    -0.42
    POSITIVE LOGITS
    Autoritní
    0.89
     تضيفلها
    0.83
    IsMutable
    0.80
    GraphicsUnit
    0.74
    EDEFAULT
    0.70
    sidemargin
    0.70
    SourceChecksum
    0.69
     gynnwys
    0.67
    bootstrapcdn
    0.66
     transfieras
    0.66
    Activations Density 1.171%

    No Known Activations