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. 31-GEMMASCOPE-RES-16K
    6. 3178
    Prev
    Next
    INDEX
    Explanations

    elements related to programming constructs and operations, particularly those involving points and coordinates in a coding context

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

    variable assignments and declarations in source code.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oa̍t
    -0.66
     autorytatywna
    -0.49
     getNum
    -0.48
    Diweddarwch
    -0.47
     INTERESAR
    -0.45
     disambiguazione
    -0.44
     transfieras
    -0.44
     betweenstory
    -0.43
    elemField
    -0.42
     roleId
    -0.42
    POSITIVE LOGITS
     current
    1.66
     previous
    1.64
     Previous
    1.36
    previous
    1.34
    current
    1.34
     Current
    1.30
    Previous
    1.27
     CURRENT
    1.27
     currently
    1.24
     actuales
    1.24
    Activations Density 0.836%

    No Known Activations