© 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. 12-GEMMASCOPE-RES-16K
    11. 5645
    Prev
    Next
    INDEX
    Explanations

    references to "X" and related data types or variables in programming contexts

    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
    dette
    -0.45
    debounce
    -0.44
    providedIn
    -0.43
     ब्रेकडाउन
    -0.43
     LTS
    -0.43
     PPS
    -0.42
     BOP
    -0.40
    便
    -0.40
    ttf
    -0.40
    Dermott
    -0.40
    POSITIVE LOGITS
     X
    1.27
    X
    1.23
     getX
    1.09
     x
    1.05
    getX
    1.03
    setX
    0.98
    x
    0.96
    XC
    0.85
    Xavier
    0.85
     Xander
    0.84
    Activations Density 0.883%

    No Known Activations