© 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. 38977
    Prev
    Next
    INDEX
    Explanations

    the word "this" in various contexts

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

    and this followed by noun/reason

    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
     صوتيه
    -0.68
    ValueStyle
    -0.66
    :✨
    -0.62
    setVerticalGroup
    -0.60
    
    -0.57
     itſelf
    -0.57
    aarrggbb
    -0.57
    VNB
    -0.56
    ſelves
    -0.56
     müſſen
    -0.55
    POSITIVE LOGITS
     leads
    0.41
    Cyfeiriadau
    0.35
     adds
    0.35
    adomo
    0.34
     d
    0.34
     бассе
    0.33
     hence
    0.33
     וכל
    0.33
     all
    0.33
     extends
    0.33
    Activations Density 0.024%

    No Known Activations