© 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. 661
    Prev
    Next
    INDEX
    Explanations

    questions that seek to clarify understanding or inquire about the reasons behind certain actions or beliefs

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

    Questions starting with "How", "What", or "Why"

    np_acts-logits-general · gemini-2.0-flash

    how what why questions

    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
    -------
    -0.58
     يتيمه
    -0.58
    ---|---|
    -0.52
     AssemblyVersion
    -0.49
    ThroughAttribute
    -0.47
    localVar
    -0.47
    PYX
    -0.45
    mtrl
    -0.45
     Италијани
    -0.44
    出版年
    -0.43
    POSITIVE LOGITS
     conozco
    0.46
     conoce
    0.44
    ComponentModel
    0.43
     كومونز
    0.43
     conhece
    0.41
     bailarina
    0.40
     dikenal
    0.40
     krwi
    0.40
     nahilalakip
    0.40
     conocen
    0.39
    Activations Density 0.192%

    No Known Activations