Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 72733
    Prev
    Next
    INDEX
    Explanations

    phrases that express uncertainty or the need for clarification

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

    saying words

    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
     GenerationType
    -0.52
    AISSEE
    -0.49
    Билгалдахарш
    -0.48
     الرياضيه
    -0.47
    ukone
    -0.47
     vPvB
    -0.44
    ThroughAttribute
    -0.43
    μφωνα
    -0.43
    CascadeType
    -0.43
    󠁣
    -0.42
    POSITIVE LOGITS
     speechless
    0.51
     words
    0.45
     simply
    0.41
     about
    0.41
     synonymous
    0.40
    ame
    0.40
    一言
    0.39
     Simplemente
    0.39
    sendRedirect
    0.38
     RESPECT
    0.38
    Activations Density 0.008%

    No Known Activations