© 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. 18-GEMMASCOPE-RES-16K
    6. 3928
    Prev
    Next
    INDEX
    Explanations

    URLs and references to web resources

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

    URLs, often with "http" or "https"

    np_acts-logits-general · gemini-2.0-flash

    http and https urls

    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
    WebElementEntity
    -0.87
    >";
    
    -0.77
    DeleteBehavior
    -0.72
    addCriterion
    -0.69
     <>",
    -0.65
     ?";
    -0.63
    ">
    
    
    -0.62
    >
    
    
    -0.61
    PointerException
    -0.60
     Exactos
    -0.60
    POSITIVE LOGITS
    ://
    0.63
    Portail
    0.51
     հղումներ
    0.49
     krop
    0.47
    VersionUID
    0.46
     esterni
    0.45
    onedDateTime
    0.44
     Maury
    0.43
    AddTagHelper
    0.43
     بيها
    0.41
    Activations Density 0.135%

    No Known Activations