© 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. 9-GEMMASCOPE-RES-131K
    6. 82593
    Prev
    Next
    INDEX
    Explanations

    words indicating confirmation or affirmation

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

    confirmed that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    writerow
    -0.48
     beginnetje
    -0.41
    änglich
    -0.41
     verdieping
    -0.40
     distract
    -0.39
     defaultstate
    -0.39
    ReusableCell
    -0.39
     houden
    -0.38
    rapie
    -0.37
    decoración
    -0.37
    POSITIVE LOGITS
     confirmed
    1.06
     Confirmed
    0.94
     confirms
    0.93
     confirmó
    0.90
     confirm
    0.90
    confirmed
    0.86
     confirmé
    0.86
     Confirm
    0.86
     confirming
    0.84
    Confirm
    0.84
    Activations Density 0.006%

    No Known Activations