Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 1076
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions related to factors and equations

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

    Mathematical equations/expressions

    np_acts-logits-general · gemini-2.0-flash

    greatest common factor

    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
    urantes
    -0.36
    enschappen
    -0.36
    consulté
    -0.35
     expectation
    -0.35
    OrWhiteSpace
    -0.35
     Santander
    -0.35
    atina
    -0.34
    調
    -0.33
    Compat
    -0.33
    ücks
    -0.33
    POSITIVE LOGITS
    AndEndTag
    1.13
     CreateTagHelper
    0.68
     newBuilder
    0.53
     disambiguazione
    0.53
    \{\\
    0.51
    complexContent
    0.51
     مرئيه
    0.49
    wiſe
    0.49
    forName
    0.46
    ništ
    0.45
    Activations Density 0.843%

    No Known Activations