© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 7992
    Prev
    Next
    INDEX
    Explanations

    code syntax and programming constructs related to data structures and algorithmic logic

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

    Mathematical or code symbols

    np_acts-logits-general · gemini-2.0-flash

    comparison operators and mathematical variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     equ
    -0.65
    Equ
    -0.60
     Equ
    -0.58
    equ
    -0.57
     EQU
    -0.56
     equal
    -0.54
    equal
    -0.52
     equi
    -0.50
    equals
    -0.49
     matching
    -0.48
    POSITIVE LOGITS
     >
    0.72
    }>\
    0.64
     $>$
    0.63
     >
    0.60
     <
    0.59
    小于
    0.59
    ＞
    0.55
     $>
    0.55
     <",
    0.55
     greater
    0.54
    Activations Density 0.714%

    No Known Activations