© 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. 9555
    Prev
    Next
    INDEX
    Explanations

    forward slashes in the text, indicating file paths or code segments

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

    java, resources, or code paths

    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
    +#+#
    -0.69
    principalColumn
    -0.63
    tagext
    -0.62
    IVEREF
    -0.61
     CreateTagHelper
    -0.59
    tonode
    -0.58
     arşivlendi
    -0.58
    EditorBrowsable
    -0.57
     disambiguazione
    -0.57
     Taktlose
    -0.57
    POSITIVE LOGITS
    resources
    0.46
     java
    0.39
    java
    0.39
     resources
    0.39
     Java
    0.38
     Resources
    0.36
     hom
    0.35
     encant
    0.34
     chemistry
    0.34
    ねて
    0.33
    Activations Density 0.002%

    No Known Activations