Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 15-GEMMASCOPE-RES-16K
    6. 5122
    Prev
    Next
    INDEX
    Explanations

    log and debug statements 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
    __':
    
    -0.87
    __":
    
    -0.72
    .~(\
    -0.71
     mxArray
    -0.67
    __':
    -0.66
    .";
    
    -0.65
    ']):
    -0.64
     ?',
    -0.64
     CreateTagHelper
    -0.64
    HtmlAttribute
    -0.62
    POSITIVE LOGITS
    --
    0.53
    inį
    0.52
     fuck
    0.51
    rrrr
    0.50
     hello
    0.50
    !
    0.50
    etna
    0.50
    ulen
    0.50
     here
    0.50
    ----
    0.49
    Activations Density 0.122%

    No Known Activations