© 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-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 5434
    Prev
    Next
    INDEX
    Explanations

    technology and numeric identifiers associated with data or specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RTSN
    -0.40
    epam
    -0.37
     Einf
    -0.35
     proper
    -0.35
     Satz
    -0.34
     DD
    -0.34
     Dö
    -0.34
     …
    -0.34
     Sorg
    -0.33
     Aug
    -0.33
    POSITIVE LOGITS
    assium
    0.78
     K
    0.75
    K
    0.74
    K
    0.73
     Kombat
    0.72
     Kard
    0.72
    KP
    0.71
     Kendra
    0.70
     Kear
    0.68
    KF
    0.68
    Activations Density 1.318%

    No Known Activations