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. 16-GEMMASCOPE-RES-16K
    6. 12697
    Prev
    Next
    INDEX
    Explanations

    title-like structures, particularly headings or section titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GOTREF
    -0.53
     Roskov
    -0.49
    Personensuche
    -0.44
     resourceCulture
    -0.43
     actualidad
    -0.43
    ThroughAttribute
    -0.43
    Anyhow
    -0.42
     flesta
    -0.42
    fromnode
    -0.41
     виправивши
    -0.41
    POSITIVE LOGITS
     Hip
    0.54
     quæ
    0.52
    bootstrapcdn
    0.52
     critical
    0.50
    enges
    0.50
    Exp
    0.49
    Hip
    0.49
    Espan
    0.49
     EXP
    0.48
     relationship
    0.48
    Activations Density 0.076%

    No Known Activations