© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 90855
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to form validation in HTML or programming environments

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

    character length and size

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    complexContent
    -0.56
    twimg
    -0.56
     tartalomajánló
    -0.55
    RTEE
    -0.54
     FetchType
    -0.53
    withIdentifier
    -0.53
     &___
    -0.52
     HttpNotFound
    -0.51
     חיצוניים
    -0.51
    AutoScaleMode
    -0.49
    POSITIVE LOGITS
    Character
    0.42
     characters
    0.42
    characters
    0.40
     character
    0.40
     legyen
    0.39
     shortening
    0.38
     length
    0.38
    length
    0.38
     karakter
    0.38
     글
    0.38
    Activations Density 0.006%

    No Known Activations