© 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 EvalsExportsinterp-engineNEWAPI 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. 61394
    Prev
    Next
    INDEX
    Explanations

    elements related to character alignment and interactions in a narrative context

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

    alignment, disposition, and relationships

    np_acts-logits-general · gemini-2.5-flash-lite

    tokens that signal a character's or group's allegiance, moral stance, or relational alignment (e.g., who is allied, hostile, good/bad, or betrayed).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    centiles
    -0.42
    PostInfinity
    -0.41
    etCode
    -0.40
     bruja
    -0.39
    IsContent
    -0.38
     Efq
    -0.38
     appelez
    -0.37
     edades
    -0.36
     Herramientas
    -0.36
     droga
    -0.35
    POSITIVE LOGITS
     friendly
    0.54
    friendly
    0.49
    تقاوى
    0.49
     Friendly
    0.45
    peace
    0.45
     uğ
    0.44
     peace
    0.42
    TagHelpers
    0.42
     AssemblyCompany
    0.41
    RatingBar
    0.41
    Activations Density 0.190%

    No Known Activations