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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 5830
    Prev
    Next
    INDEX
    Explanations

    patterns related to structured data identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مرئيه
    -0.52
     OFDb
    -0.47
    setcounter
    -0.47
    __":
    
    -0.47
    󠁣
    -0.47
    orsese
    -0.46
     kaynağından
    -0.42
     autorytatywna
    -0.42
    Personensuche
    -0.40
     GenerationType
    -0.40
    POSITIVE LOGITS
    Trans
    0.43
    titleMargin
    0.42
     Schna
    0.42
    gemä
    0.41
     continúa
    0.41
    Play
    0.40
    GeneratedCode
    0.40
     titolata
    0.39
     Play
    0.38
     expresa
    0.38
    Activations Density 0.353%

    No Known Activations