© 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. 114886
    Prev
    Next
    INDEX
    Explanations

    JavaScript functions that manipulate DOM classes or throw errors

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

    add class or remove attribute

    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
     catchment
    -0.52
    tvguidetime
    -0.51
    nativeElement
    -0.50
    lectoral
    -0.49
    expandindo
    -0.48
    StandardCharsets
    -0.48
    ItemGroup
    -0.48
    temon
    -0.47
     sirens
    -0.47
     ['./
    -0.46
    POSITIVE LOGITS
    removeClass
    1.55
    AppendLine
    0.87
    removeAttr
    0.61
    removeAttribute
    0.59
     TMPro
    0.55
    shadowOpacity
    0.49
    toThrow
    0.49
    addClass
    0.47
    HasColumnType
    0.46
    toggleClass
    0.46
    Activations Density 0.000%

    No Known Activations