© 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. 25-GEMMASCOPE-RES-16K
    11. 1084
    Prev
    Next
    INDEX
    Explanations

    references to ongoing investigations and related legal matters

    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
     estimés
    -0.88
    Gambas
    -0.69
    brainly
    -0.60
     répondu
    -0.57
     MonoBehaviour
    -0.56
    bootstrapcdn
    -0.56
    featureID
    -0.55
     متعلقه
    -0.55
     aufmerksam
    -0.54
     nakalista
    -0.54
    POSITIVE LOGITS
     copies
    0.82
     proof
    0.76
     affidavits
    0.75
     documentation
    0.74
     evidence
    0.71
     video
    0.70
     receipts
    0.70
     names
    0.69
     documents
    0.67
     screenshots
    0.66
    Activations Density 0.765%

    No Known Activations