© 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. 25-GEMMASCOPE-RES-16K
    6. 3235
    Prev
    Next
    INDEX
    Explanations

    specific sequences and codes related to molecular biology, particularly in the context of primers and reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    S
    -0.86
    E
    -0.75
    A
    -0.73
    I
    -0.72
    C
    -0.71
    O
    -0.69
    EI
    -0.68
    uilla
    -0.68
    EJ
    -0.66
    AAT
    -0.66
    POSITIVE LOGITS
    Referanser
    0.45
    J
    0.44
    RunAsync
    0.42
    idée
    0.42
     mergeFrom
    0.42
    
    0.41
    decorative
    0.40
    Quiénes
    0.40
    Q
    0.40
    Statistiche
    0.39
    Activations Density 0.976%

    No Known Activations