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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 107593
    Prev
    Next
    INDEX
    Explanations

    attribute assignments in HTML or XML elements

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

    javascript class names

    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
     AssemblyCulture
    -0.96
    Tikang
    -0.92
    تقاوى
    -0.82
    expandindo
    -0.81
    ðsíða
    -0.79
    rungsseite
    -0.79
     disambiguazione
    -0.79
     JpaRepository
    -0.79
     desmotivaciones
    -0.79
    səhifə
    -0.79
    POSITIVE LOGITS
    className
    0.52
     $(".
    0.51
     $('.
    0.48
    $('.
    0.48
     an
    0.48
     a
    0.45
    ('.
    0.44
    s
    0.44
    ↵↵
    0.44
     d
    0.42
    Activations Density 0.010%

    No Known Activations