© 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. 108152
    Prev
    Next
    INDEX
    Explanations

    key pieces of information that indicate the presence of significant or influential factors in a text

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

    materials and ecosystem services

    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
    MessageTagHelper
    -0.78
     CreateTagHelper
    -0.72
     tartalomajánló
    -0.71
    новниш
    -0.65
    thâu
    -0.65
    ніципалі
    -0.64
    LookAnd
    -0.62
     wikipagina
    -0.61
    IndentedString
    -0.60
    rrggbb
    -0.60
    POSITIVE LOGITS
     поза
    0.31
    arschu
    0.31
     battle
    0.29
    ähig
    0.29
     tas
    0.28
     ми
    0.28
     instant
    0.27
     подо
    0.27
    ，
    0.27
    a
    0.26
    Activations Density 0.027%

    No Known Activations