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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 25002
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and quotation marks used in various contexts

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

    quoted strings and code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.71
    transQ
    -0.63
    SuppressLint
    -0.63
     Zola
    -0.63
     Zucchini
    -0.62
     Saline
    -0.62
    hloromethane
    -0.62
    fxml
    -0.62
    发表于
    -0.61
    enfone
    -0.61
    POSITIVE LOGITS
     "'
    1.18
    "'
    1.16
    ="'
    1.00
    ("'
    0.95
    }'
    0.84
    ."'
    0.82
    +"'
    0.79
    )'
    0.78
    ]'
    0.71
    >'
    0.70
    Activations Density 0.017%

    No Known Activations