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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 2227
    Prev
    Next
    INDEX
    Explanations

    references to mathematical equations, definitions, and propositions within the text

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

    Referring to equations (Eq)

    np_acts-logits-general · gemini-2.0-flash

    equation references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
     незавершена
    -0.58
    sizeCache
    -0.57
    новниш
    -0.56
    AsUp
    -0.55
     davon
    -0.54
    Personensuche
    -0.54
     Италијани
    -0.52
    TypedDataSet
    -0.51
    Parcelize
    -0.51
    Autoritní
    -0.50
    POSITIVE LOGITS
     Eq
    1.15
     Equation
    1.10
     equation
    1.08
     eq
    1.02
    Eq
    0.93
    Equation
    0.91
     Eqs
    0.91
     eqn
    0.91
    eq
    0.90
     equations
    0.87
    Activations Density 0.869%

    No Known Activations