© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 7735
    Prev
    Next
    INDEX
    Explanations

    programming terminology related to data structures and algorithms

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

    Code substrings and object properties

    np_acts-logits-general · gemini-2.0-flash

    identifying list elements

    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
    ">—
    -0.40
    addComponent
    -0.39
     {}".
    -0.39
    ╝
    -0.37
    InfoWindow
    -0.37
     мәкал
    -0.36
    addCell
    -0.36
     {}'.
    -0.36
    ͅ
    -0.36
    {}'.
    -0.35
    POSITIVE LOGITS
    
    0.68
     ModelExpression
    0.57
     Paglinawan
    0.56
     Exactos
    0.51
    zczegól
    0.51
     المعيارى
    0.47
     mandatario
    0.45
    ########.
    0.44
     Audiodateien
    0.44
     Ressources
    0.43
    Activations Density 0.236%

    No Known Activations