© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 3059
    Prev
    Next
    INDEX
    Explanations

    print statements and output functions 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 @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ')['
    -0.67
     صوتيه
    -0.66
    "]();
    -0.65
     ostavi
    -0.62
    ]--;
    -0.61
     >=",
    -0.60
     فريبيس
    -0.59
     bArr
    -0.59
    ритори
    -0.56
     Nusa
    -0.56
    POSITIVE LOGITS
    println
    0.75
    WriteLine
    0.71
    Println
    0.70
    fillText
    0.62
    Zeneca
    0.62
     prints
    0.61
    enderror
    0.60
     printed
    0.59
    //
    0.59
     CURIAM
    0.56
    Activations Density 0.044%

    No Known Activations