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. 12-GEMMASCOPE-RES-16K
    6. 2045
    Prev
    Next
    INDEX
    Explanations

    code structure related to error handling and success callbacks in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    leich
    -0.32
     Maher
    -0.31
     Bengal
    -0.29
    OCOL
    -0.29
    ToolTip
    -0.29
    mak
    -0.29
     Cavity
    -0.29
     Inn
    -0.28
     mak
    -0.28
    zur
    -0.28
    POSITIVE LOGITS
    GOTREF
    0.81
    FailureListener
    0.80
     Infórmanos
    0.68
    DockStyle
    0.68
    InputBorder
    0.63
    PreInfinity
    0.61
     المعيارى
    0.61
     يتيمه
    0.60
    StoreMessageInfo
    0.59
     onFailure
    0.58
    Activations Density 0.495%

    No Known Activations