© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 9884
    Prev
    Next
    INDEX
    Explanations

    various list and array structures in code

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

    Code snippets and programming constructs

    np_acts-logits-general · gemini-2.0-flash

    list initializations or programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /*
    -0.31
    ConstraintMaker
    -0.28
     over
    -0.27
    FDRE
    -0.26
    enteri
    -0.26
    inc
    -0.26
    gcf
    -0.25
     $('#
    -0.25
    gerufen
    -0.25
     đu
    -0.25
    POSITIVE LOGITS
    rungsseite
    0.79
     ([]
    0.67
     betweenstory
    0.66
    NSMutableArray
    0.65
    IsMutable
    0.64
     []*
    0.63
     ARRAY
    0.62
     Inſ
    0.62
    estacks
    0.62
    =[]
    0.60
    Activations Density 0.458%

    No Known Activations