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. 1523
    Prev
    Next
    INDEX
    Explanations

    variables and parameters related to game mechanics and player interactions

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

    Code, configuration, or rules related to game logic

    np_acts-logits-general · gemini-2.0-flash

    player mark and interval control

    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
    Globals
    -0.54
    ishments
    -0.50
    '),
    
    -0.50
     potentially
    -0.49
     computationally
    -0.49
    mands
    -0.48
     slated
    -0.46
     amongst
    -0.46
    TextAlignment
    -0.46
     prefs
    -0.46
    POSITIVE LOGITS
     AssemblyCulture
    1.01
    StructEnd
    0.69
    MessageOf
    0.67
     kasarigan
    0.67
    новништво
    0.66
    AddTagHelper
    0.66
     Beside
    0.65
     púb
    0.65
     pleaſure
    0.65
    EndProject
    0.65
    Activations Density 0.065%

    No Known Activations