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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1362
    Prev
    Next
    INDEX
    Explanations

    specific programming terminologies and code identifiers used in data management and hardware interfacing

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

    Hexadecimal numbers and code

    np_acts-logits-general · gemini-2.0-flash

    CD one

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RectangleBorder
    -0.48
    atguigu
    -0.47
     Gelegenheit
    -0.45
     Schmitz
    -0.44
     Spitze
    -0.44
     temperatuur
    -0.43
     Ausbau
    -0.43
     Stirn
    -0.42
     duidelijk
    -0.42
    providedIn
    -0.42
    POSITIVE LOGITS
    HasAnnotation
    0.47
     ProtoMessage
    0.45
     Endoc
    0.43
    انجليز
    0.43
     Skys
    0.43
    andoah
    0.43
     المعيارى
    0.42
    EnableWeb
    0.41
    webf
    0.40
    ngdoc
    0.40
    Activations Density 0.377%

    No Known Activations