© 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. 13030
    Prev
    Next
    INDEX
    Explanations

    technical terminology associated with coding and programming constructs

    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
    oneg
    -0.40
    Diweddarwch
    -0.39
     asses
    -0.39
     breeding
    -0.39
     Seg
    -0.38
    zcze
    -0.38
     invokingState
    -0.38
     Mig
    -0.38
     bearers
    -0.37
     grads
    -0.37
    POSITIVE LOGITS
    PrintStream
    0.57
    stream
    0.49
    httphttps
    0.49
     BorderSide
    0.46
    PullParser
    0.44
    JspWriter
    0.44
    CodedInputStream
    0.43
    XmlIgnore
    0.41
    bufio
    0.40
     stream
    0.40
    Activations Density 0.406%

    No Known Activations