© 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. 39134
    Prev
    Next
    INDEX
    Explanations

    terms related to logical and natural progressions or extensions in ideas

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

    logical or natural extension

    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
     indépendante
    -0.42
     judiciaire
    -0.38
     désol
    -0.38
     indépendant
    -0.37
     Substanz
    -0.37
     láser
    -0.36
     escuchado
    -0.36
     prétend
    -0.33
     aislado
    -0.33
     juridique
    -0.33
    POSITIVE LOGITS
     logically
    0.81
     logical
    0.72
     naturally
    0.72
     Logical
    0.69
    Naturally
    0.69
    Obvious
    0.67
    naturally
    0.66
     Naturally
    0.64
     naturlig
    0.64
     логи
    0.59
    Activations Density 0.040%

    No Known Activations