Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 39038
    Prev
    Next
    INDEX
    Explanations

    conditional statements and checks for null values

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

    conditional logic with null checks

    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
    TintMode
    -0.45
    NewLabel
    -0.45
    abstractmethod
    -0.42
    nloa
    -0.39
    ustimmung
    -0.36
     Francus
    -0.35
     ember
    -0.35
    矢
    -0.35
     apply
    -0.35
     findAll
    -0.35
    POSITIVE LOGITS
    MigrationBuilder
    0.56
    Geplaatst
    0.49
     onCreateView
    0.47
    rungsseite
    0.45
    IVEREF
    0.42
     tartalomajánló
    0.41
    getClassLoader
    0.41
     kasarigan
    0.40
    aarrggbb
    0.40
    ंदीखरीदारी
    0.39
    Activations Density 0.001%

    No Known Activations