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

    Neuronpedia

    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. 23-GEMMASCOPE-RES-16K
    11. 2359
    Prev
    Next
    INDEX
    Explanations

    data types and structures related to byte arrays and binary data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ScopeManager
    -0.49
    )_{\
    -0.48
    __':
    -0.47
     TestBed
    -0.46
    __':
    -0.44
     aikaa
    -0.44
     Roosevelt
    -0.44
     AspNetCore
    -0.44
    __":
    -0.43
     drenaje
    -0.43
    POSITIVE LOGITS
    byte
    1.07
     byte
    1.05
    Byte
    0.96
     Byte
    0.82
    getBytes
    0.79
    Bytes
    0.77
     BYTE
    0.77
    bytes
    0.75
    BYTE
    0.71
     Bytes
    0.69
    Activations Density 0.322%

    No Known Activations