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. 3-GEMMASCOPE-RES-16K
    6. 8268
    Prev
    Next
    INDEX
    Explanations

    patterns related to error messages or status codes from system calls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.87
     Pogba
    -0.81
     Toul
    -0.81
    fulness
    -0.78
    yyah
    -0.75
    tabular
    -0.75
    dah
    -0.72
     Valenzuela
    -0.72
     Tash
    -0.70
     Caul
    -0.70
    POSITIVE LOGITS
             
    1.14
    odeon
    0.88
     Niki
    0.85
    -----------
    0.83
     ---------
    0.83
    theless
    0.81
     wic
    0.81
     PFA
    0.80
    ICP
    0.78
     Marquez
    0.76
    Activations Density 0.107%

    No Known Activations