© 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. 21-GEMMASCOPE-RES-16K
    11. 12806
    Prev
    Next
    INDEX
    Explanations

    strings of variable-like identifiers or references in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.75
    ="@+
    -0.69
    UnknownFieldSet
    -0.66
    󠁴
    -0.65
     tartalomajánló
    -0.60
    ########.
    -0.59
     MainAxisSize
    -0.59
     zoude
    -0.58
     betweenstory
    -0.57
    principalColumn
    -0.57
    POSITIVE LOGITS
    devamını
    0.51
    expandindo
    0.46
     Semarang
    0.38
     despe
    0.37
     marihuana
    0.35
     daños
    0.33
    TagMode
    0.33
     damages
    0.32
     cuerda
    0.31
     Rockstar
    0.30
    Activations Density 1.559%

    No Known Activations