© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 107687
    Prev
    Next
    INDEX
    Explanations

    components related to menu options in a programming context

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

    onCreateOptionsMenu

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (&:
    -0.43
     zufolge
    -0.42
     estudantes
    -0.42
     travailleurs
    -0.42
     Hentet
    -0.41
    uVar
    -0.41
     médecins
    -0.40
     récit
    -0.38
     Albrecht
    -0.38
     Atual
    -0.38
    POSITIVE LOGITS
    OptionsMenu
    5.56
     onOptions
    1.52
    StoryboardSegue
    0.99
    HomeAsUpEnabled
    0.96
    MenuInflater
    0.91
    IntoConstraints
    0.84
    ReusableCell
    0.83
    SupportActionBar
    0.81
    menuStrip
    0.79
    onOptions
    0.73
    Activations Density 0.000%

    No Known Activations