© 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. 28-GEMMASCOPE-RES-16K
    11. 9633
    Prev
    Next
    INDEX
    Explanations

    descriptions and definitions related to various types of objects and their characteristics

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

    Comes before a definition

    np_acts-logits-general · gemini-2.0-flash

    definitions and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pinulongan
    -0.73
     يتيمه
    -0.67
    hyrchwyd
    -0.64
     للاسماء
    -0.63
     galore
    -0.60
    ècie
    -0.60
    vania
    -0.59
    hoeddwyd
    -0.59
    lwjgl
    -0.56
    utnik
    -0.56
    POSITIVE LOGITS
     usually
    0.57
     zwykle
    0.54
    usually
    0.49
     biasanya
    0.47
     typically
    0.47
     geralmente
    0.46
     Usually
    0.46
    Usually
    0.46
     généralement
    0.45
     habituellement
    0.41
    Activations Density 0.744%

    No Known Activations