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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 669
    Prev
    Next
    INDEX
    Explanations

    parentheses in various contexts

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

    anthology, weather, peace, noiseless

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.60
    awtextra
    -0.42
    VersionUID
    -0.40
    CppMethod
    -0.40
     ''),
    -0.40
    SizeF
    -0.39
    도록
    -0.38
     تضيفلها
    -0.38
    ineno
    -0.37
    므로
    -0.36
    POSITIVE LOGITS
     autorytatywna
    0.50
    NameInMap
    0.49
    Personensuche
    0.48
     nahilalakip
    0.47
    dengar
    0.47
    setVerticalGroup
    0.45
    enterOuterAlt
    0.45
    érc
    0.43
     ComVisible
    0.42
    stateProvider
    0.42
    Activations Density 0.120%

    No Known Activations