Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 56818
    Prev
    Next
    INDEX
    Explanations

    terminology related to snapshots in various contexts

    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
     Lo
    -0.69
     thiệu
    -0.68
     fleste
    -0.68
    stdbool
    -0.66
     bekas
    -0.66
    возмо
    -0.64
    IBinder
    -0.63
     hjemme
    -0.63
     drogas
    -0.63
     lo
    -0.62
    POSITIVE LOGITS
     Snapshot
    1.83
     snapshot
    1.80
    Snapshot
    1.76
     snapshots
    1.73
    snapshots
    1.55
    snapshot
    1.46
    pshots
    1.45
    Snapshots
    1.45
    DataSnapshot
    1.30
     Sna
    1.27
    Activations Density 0.006%

    No Known Activations