© 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. 30-GEMMASCOPE-RES-16K
    11. 10050
    Prev
    Next
    INDEX
    Explanations

    programming constructs and data manipulation instructions

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

    Deals with bytes and hexadecimal values

    np_acts-logits-general · gemini-2.0-flash

    byte values and hex codes

    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
    RTLR
    -0.68
    matchCondition
    -0.62
    AsUp
    -0.57
     مشين
    -0.55
     noDo
    -0.55
     iprot
    -0.55
    RegressionTest
    -0.54
     nahilalakip
    -0.54
     resourceCulture
    -0.53
    Ӕ
    -0.51
    POSITIVE LOGITS
     byte
    0.62
    byte
    0.57
    Byte
    0.45
    BYTE
    0.44
     bytes
    0.39
     Byte
    0.38
    bytes
    0.38
    WriteByte
    0.38
    InBytes
    0.37
     chaff
    0.35
    Activations Density 2.260%

    No Known Activations