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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 13118
    Prev
    Next
    INDEX
    Explanations

    references to the action of managing or dealing with tasks, processes, or entities

    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
     surla
    -0.60
    elemField
    -0.52
    AutoField
    -0.51
     BoxFit
    -0.50
    setLayoutParams
    -0.49
    الحياه
    -0.48
    ReusableCell
    -0.48
    niająca
    -0.47
    PyTuple
    -0.46
     purpoſe
    -0.45
    POSITIVE LOGITS
     handle
    2.50
     Handle
    2.22
     handles
    2.11
    handle
    2.03
    Handle
    1.94
     HANDLE
    1.84
     Handles
    1.80
     handled
    1.73
    handles
    1.70
    Handles
    1.55
    Activations Density 0.128%

    No Known Activations