© 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. 9-GEMMASCOPE-RES-131K
    6. 17540
    Prev
    Next
    INDEX
    Explanations

    patterns related to type checking in programming

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

    checking object type or class

    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
    gelegt
    -0.45
     charité
    -0.44
    LEGGI
    -0.44
     então
    -0.43
     tekrar
    -0.42
     Gerechtigkeit
    -0.41
    gnügen
    -0.40
    ContentAsync
    -0.39
     Pfar
    -0.39
    tablir
    -0.38
    POSITIVE LOGITS
     isinstance
    3.36
    isinstance
    2.47
     hasattr
    1.00
     isKindOfClass
    1.00
     instanceof
    0.83
    isArray
    0.82
    arraycopy
    0.69
    strcmp
    0.68
    setof
    0.67
     strcmp
    0.67
    Activations Density 0.002%

    No Known Activations