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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 12424
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations or areas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    encyclopedias or informational content

    np_acts-logits-general · gemini-2.0-flash

    encyclopedias and informational websites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Announced
    -0.46
    发表于
    -0.45
    Copies
    -0.45
     leaked
    -0.44
    alamualaikum
    -0.43
     Contacto
    -0.43
    calciatore
    -0.42
     convaincre
    -0.42
     Announcements
    -0.41
     Scanning
    -0.41
    POSITIVE LOGITS
     Britannica
    0.72
     wikihow
    0.63
    Encyclopædia
    0.56
    annica
    0.55
     encyclopedia
    0.55
    /**
    0.55
    opedia
    0.53
     Encyclopedia
    0.52
    encyclo
    0.48
     wiki
    0.48
    Activations Density 0.425%

    No Known Activations