© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 54026
    Prev
    Next
    INDEX
    Explanations

    terms related to associations or connections between concepts or items

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

    associated with

    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
    ChildScrollView
    -0.51
     Redacción
    -0.43
     emperador
    -0.40
    prevState
    -0.40
     Kro
    -0.39
     TextInputType
    -0.39
     (!_
    -0.39
    Océ
    -0.38
     simplesmente
    -0.38
     ​​
    -0.38
    POSITIVE LOGITS
     associating
    0.93
     associated
    0.93
    associated
    0.86
     Associated
    0.85
     associ
    0.85
     ASSOCIATED
    0.84
    Associated
    0.82
     association
    0.82
     associate
    0.82
     Associ
    0.81
    Activations Density 0.036%

    No Known Activations