© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 83329
    Prev
    Next
    INDEX
    Explanations

    parameters and coefficients related to mathematical or physical functions and models

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

    depends on parameter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.70
    StoryboardSegue
    -0.60
    iſen
    -0.56
    ylem
    -0.55
    ionales
    -0.53
     protoimpl
    -0.53
    ErrUnexpectedEOF
    -0.52
     palaces
    -0.51
    rungsseite
    -0.50
    richTextPanel
    -0.50
    POSITIVE LOGITS
     consider
    0.37
    RetentionPolicy
    0.34
     length
    0.31
     дописавши
    0.31
     depending
    0.28
     charakterysty
    0.28
     consideration
    0.28
    /***/
    0.27
     chứ
    0.27
     pochod
    0.27
    Activations Density 0.367%

    No Known Activations