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. 18-GEMMASCOPE-RES-16K
    6. 14354
    Prev
    Next
    INDEX
    Explanations

    directives and conditions in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Lines starting with "#define" or "#include"

    np_acts-logits-general · gemini-2.0-flash

    C/C++ preprocessor directives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Audiodateien
    -0.81
    inheit
    -0.76
    abestanden
    -0.73
    expandindo
    -0.66
    udadera
    -0.66
    )];
    
    -0.65
     }}$}
    -0.64
     الرياضيه
    -0.64
    ={({
    -0.64
     GetEnumerator
    -0.64
    POSITIVE LOGITS
    .#
    1.17
     #
    1.13
    \#
    0.95
    )#
    0.94
    :#
    0.93
     \#
    0.93
    -#
    0.90
    /#
    0.90
     (#
    0.89
    \#\#
    0.88
    Activations Density 0.244%

    No Known Activations