© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 4184
    Prev
    Next
    INDEX
    Explanations

    phrases related to purpose or intent

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

    for the sake of

    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
     насељу
    -0.41
     Insel
    -0.39
     ainfi
    -0.39
     nowhere
    -0.36
     выда
    -0.36
    brev
    -0.36
     Erscheinung
    -0.36
    DOCTYPE
    -0.35
    matchCondition
    -0.35
    OCCURRED
    -0.35
    POSITIVE LOGITS
    为了
    0.94
    是为了
    0.90
    為了
    0.90
    ůli
    0.88
    GEBURTSDATUM
    0.81
    เพื่อ
    0.71
    のために
    0.71
     sake
    0.69
     purposes
    0.68
     purpose
    0.67
    Activations Density 0.011%

    No Known Activations