© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 514
    Prev
    Next
    INDEX
    Explanations

    assignment statements and function calls in programming code

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

    assignment operators in code, particularly the equals sign used to assign values to variables.

    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
     betweenstory
    -0.54
     concub
    -0.51
     للاسماء
    -0.49
     متعلقه
    -0.47
    RTDA
    -0.45
     autorytatywna
    -0.45
    rawDesc
    -0.45
    transQ
    -0.44
    TryDecodeAsNil
    -0.44
    featureID
    -0.43
    POSITIVE LOGITS
     require
    0.64
    require
    0.64
    RegressionTest
    0.46
    Require
    0.43
     requer
    0.39
     required
    0.39
    setupUi
    0.38
    balleur
    0.37
     requires
    0.36
     kaynağından
    0.36
    Activations Density 0.138%

    No Known Activations