© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 6508
    Prev
    Next
    INDEX
    Explanations

    HTML elements related to radio buttons and form inputs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pyx
    -0.63
     /\.(
    -0.62
    Scroll
    -0.60
    WindowConstants
    -0.59
     limit
    -0.58
     Scroll
    -0.58
     scroll
    -0.57
    Hauptartikel
    -0.57
    BuildContext
    -0.55
    ]]);
    -0.55
    POSITIVE LOGITS
     checkbox
    0.88
    CheckedChanged
    0.84
    JRadioButton
    0.83
    RadioButton
    0.81
     Checkbox
    0.80
    checked
    0.78
    setChecked
    0.77
    Checkbox
    0.75
    Checked
    0.74
    checkable
    0.73
    Activations Density 0.138%

    No Known Activations