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

    Neuronpedia

    Jacobian LensNEW
    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. 15884
    Prev
    Next
    INDEX
    Explanations

    the word "always" and phrases indicating consistency or positive experiences

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

    always followed by a descriptor

    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
     polig
    -0.47
     autorytatywna
    -0.46
    addPreferredGap
    -0.43
     للاسماء
    -0.43
     estekak
    -0.42
    dataclass
    -0.41
     ProtoMessage
    -0.41
    kháu
    -0.41
    RenderAtEndOf
    -0.40
    thâu
    -0.39
    POSITIVE LOGITS
     always
    0.78
    always
    0.73
    Always
    0.72
     selalu
    0.72
     zawsze
    0.71
     siempre
    0.69
     תמיד
    0.67
     Always
    0.67
     altijd
    0.67
     sempre
    0.66
    Activations Density 0.014%

    No Known Activations