© 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
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8768
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "handle" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     managed
    -0.39
     intptr
    -0.38
     resultCode
    -0.37
     specified
    -0.36
     network
    -0.35
    writeValue
    -0.35
    Sprintf
    -0.35
    сылкі
    -0.35
    orianCalendar
    -0.34
    dienst
    -0.34
    POSITIVE LOGITS
    Handle
    1.03
    handle
    0.92
     Handle
    0.82
    HANDLE
    0.69
    ハンドル
    0.59
     HANDLE
    0.59
     handle
    0.59
    Handles
    0.55
     testigo
    0.54
    Grab
    0.53
    Activations Density 0.192%

    No Known Activations