© 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. 15-GEMMASCOPE-RES-16K
    6. 5380
    Prev
    Next
    INDEX
    Explanations

    relationships between actions and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     today
    -0.39
     remaining
    -0.38
     non
    -0.37
     output
    -0.37
     re
    -0.37
     scio
    -0.36
    ime
    -0.35
     Olímp
    -0.35
     S
    -0.33
    prech
    -0.33
    POSITIVE LOGITS
     estekak
    1.08
    Lähteet
    0.92
    bewerken
    0.91
    toHaveBeenCalled
    0.87
     betweenstory
    0.87
     beginnetje
    0.85
    parsedMessage
    0.84
    Chham
    0.82
    AndEndTag
    0.82
     виправивши
    0.82
    Activations Density 0.594%

    No Known Activations