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

    Neuronpedia

    APICircuit 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 - 131k
    5. 23-GEMMASCOPE-RES-131K
    6. 23119
    Prev
    Next
    INDEX
    Explanations

    references to data sources and citations in research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    سطس
    -0.49
    ſures
    -0.43
     تضيفلها
    -0.43
    tonsoft
    -0.42
    WebControls
    -0.42
    SourceChecksum
    -0.41
    ſten
    -0.41
     faſt
    -0.40
    ſure
    -0.40
    ftagPool
    -0.40
    POSITIVE LOGITS
     from
    0.76
    from
    0.65
    来自于
    0.56
    來自
    0.56
     derives
    0.55
     FROM
    0.55
     provenant
    0.55
    来自
    0.54
     originates
    0.52
     proviene
    0.52
    Activations Density 0.132%

    No Known Activations