© 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. 24-GEMMASCOPE-RES-16K
    11. 5850
    Prev
    Next
    INDEX
    Explanations

    API commands and their parameters in a structured format

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

    Code or markup delimiters/syntax

    np_acts-logits-general · gemini-2.0-flash

    bend right

    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
     كومونز
    -0.56
    adaptiveStyles
    -0.49
    canestro
    -0.48
     AssemblyTitle
    -0.45
     MonoBehaviour
    -0.41
    initComponents
    -0.40
     GetEnumerator
    -0.40
    ImageContext
    -0.37
    UseVisualStyle
    -0.37
    Ingrédients
    -0.36
    POSITIVE LOGITS
    tagext
    0.60
    ">//
    0.56
    TagMode
    0.52
     anzi
    0.49
    parsedMessage
    0.49
     يتيمه
    0.49
    BufferException
    0.48
    帖最后由
    0.48
     Taktlose
    0.47
    UpdateCommand
    0.45
    Activations Density 0.981%

    No Known Activations