© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 56052
    Prev
    Next
    INDEX
    Explanations

    terminology associated with ambiguity, inconsistency, and differing perspectives

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

    mixed or conflicting results

    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
    RenderAtEndOf
    -0.53
    sidemargin
    -0.44
    typeorm
    -0.43
    GEBURTSDATUM
    -0.43
    DockStyle
    -0.43
    providedIn
    -0.42
    :✨
    -0.41
    FontOfSize
    -0.41
    Serenity
    -0.40
     MediatR
    -0.39
    POSITIVE LOGITS
     mixed
    0.67
     conflicted
    0.63
     ambivalent
    0.62
     conflicting
    0.58
    Mixed
    0.57
    licting
    0.54
     bittersweet
    0.54
     divided
    0.53
     Mixed
    0.52
     divisive
    0.52
    Activations Density 0.149%

    No Known Activations