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-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 7970
    Prev
    Next
    INDEX
    Explanations

    syntactic structures such as function definitions and calls in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    szám
    -0.73
     Wib
    -0.67
     Abad
    -0.66
    BagConstraints
    -0.63
    ged
    -0.62
     Boe
    -0.61
    lesh
    -0.61
    glut
    -0.60
    ogram
    -0.60
    áculos
    -0.60
    POSITIVE LOGITS
    __":
    2.06
    __":
    
    1.98
    __':
    1.97
    __':
    
    1.81
    ])):
    1.30
    >):
    1.20
     الحره
    1.19
    ))){
    1.17
     }}">
    1.15
    "])){
    1.15
    Activations Density 0.020%

    No Known Activations