© 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. 58647
    Prev
    Next
    INDEX
    Explanations

    numeric values associated with functions and programming elements

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

    111 followed by punctuation

    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
    ſicht
    -0.88
    ⟬
    -0.87
    ſehen
    -0.85
    iſche
    -0.82
    ロウィン
    -0.81
    niſſe
    -0.81
    Espèce
    -0.81
    adaptiveStyles
    -0.81
    iſchen
    -0.80
    iſen
    -0.80
    POSITIVE LOGITS
     majority
    0.59
    1
    0.40
    -
    0.39
     SSS
    0.39
    //
    0.38
    AAA
    0.38
    3
    0.38
    pp
    0.37
    ccc
    0.36
     CCC
    0.36
    Activations Density 0.052%

    No Known Activations