© 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. 5-GEMMASCOPE-RES-16K
    6. 6826
    Prev
    Next
    INDEX
    Explanations

    names and places related to historical events or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to people and names associated with events or historical contexts

    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
    Von
    -0.83
    en
    -0.82
    e
    -0.79
    er
    -0.78
    von
    -0.77
     Glaser
    -0.75
     McCar
    -0.75
    \\\
    -0.74
     Von
    -0.73
     Schmel
    -0.71
    POSITIVE LOGITS
    bootstrapcdn
    1.01
     Chwiliwch
    1.00
    kloped
    0.98
    DataAnnotations
    0.97
     ExecuteAsync
    0.94
     CNT
    0.92
    voyance
    0.91
    ArgsConstructor
    0.91
    BibitemShut
    0.91
    rsiniz
    0.90
    Activations Density 3.326%

    No Known Activations