© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 12500
    Prev
    Next
    INDEX
    Explanations

    various forms of code structure and formatting

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

    C/assembly code and data structures

    np_acts-logits-general · gemini-2.0-flash

    unsigned integer types

    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
     noDo
    -0.72
    ReadInt
    -0.51
     ویکی‌پدی
    -0.47
     Савезне
    -0.47
    LookAnd
    -0.45
     himo
    -0.45
    oa̍t
    -0.44
     wireType
    -0.44
     AppCompatTheme
    -0.43
    GetInt
    -0.42
    POSITIVE LOGITS
    uint
    0.48
     uint
    0.47
    AddTagHelper
    0.46
     UINT
    0.46
    SourceChecksum
    0.44
     unsigned
    0.41
    spin
    0.41
    UINT
    0.39
     vote
    0.39
    unsigned
    0.38
    Activations Density 0.781%

    No Known Activations