© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 13113
    Prev
    Next
    INDEX
    Explanations

    logical expressions and control structures in code

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

    Tic-tac-toe board state

    np_acts-logits-general · gemini-2.0-flash

    structured code and math

    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
     كومونز
    -0.60
    (&:
    -0.54
    XmlAccessType
    -0.53
    NSNotification
    -0.52
    hamdu
    -0.50
    FunctionFlags
    -0.48
     UIFont
    -0.47
    glClear
    -0.47
    asnya
    -0.47
     NSError
    -0.46
    POSITIVE LOGITS
    ↵
    1.79
    ↵↵
    1.14
    (
    0.90
    ↵↵↵
    0.80
    0.79
    complexContent
    0.75
    													
    0.72
    																				
    0.72
    :

    0.71
                                   
    0.71
    Activations Density 0.835%
    No Known Activations