© 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. 58895
    Prev
    Next
    INDEX
    Explanations

    phrases related to requirements and conditions in a structured format

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

    required, mandatory, or optional

    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
    eseorang
    -0.42
     "..\..\
    -0.40
     esfuerzan
    -0.40
    运作
    -0.38
    いかに
    -0.38
     nahilalakip
    -0.36
    lepiej
    -0.36
     behaving
    -0.35
     bancaria
    -0.35
     dirinya
    -0.34
    POSITIVE LOGITS
     Essential
    0.76
    Required
    0.76
     essential
    0.75
    Essential
    0.71
    required
    0.69
     Required
    0.67
    essential
    0.66
    IsRequired
    0.66
     indispens
    0.65
     essenziale
    0.65
    Activations Density 0.016%

    No Known Activations