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. 31-GEMMASCOPE-RES-16K
    6. 3260
    Prev
    Next
    INDEX
    Explanations

    programming constructs and structures, particularly related to graphical user interface elements

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

    camelCase compound words with "Panel" or "Plotter" as the second component.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.74
     propOrder
    -0.65
    StoryboardSegue
    -0.61
     تضيفلها
    -0.60
    DIPSETTING
    -0.60
     ब्रेकडाउन
    -0.58
    webElementXpaths
    -0.57
    帖最后由
    -0.57
     ſind
    -0.57
    MigrationBuilder
    -0.55
    POSITIVE LOGITS
    Autoritní
    0.41
    [toxicity=0]
    0.38
    uscular
    0.37
    anglès
    0.35
    ();
    
    
    0.34
    ांकि
    0.33
    ly
    0.32
    <bos>
    0.32
     litté
    0.31
    ી
    0.30
    Activations Density 1.367%

    No Known Activations