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. 25-GEMMASCOPE-RES-16K
    6. 12451
    Prev
    Next
    INDEX
    Explanations

    elements related to visual representation and descriptions in the context of guidelines or technical advice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VertexArray
    -0.44
     palvel
    -0.41
     pleaſure
    -0.41
     gloire
    -0.41
     voren
    -0.41
     poitrine
    -0.41
    manuelle
    -0.40
     beauté
    -0.39
    еня
    -0.39
     medesimo
    -0.39
    POSITIVE LOGITS
    ształ
    0.56
    ))^{
    0.53
    lappe
    0.51
     createSlice
    0.51
    jenner
    0.48
    enapa
    0.45
     Crimea
    0.45
    anskje
    0.43
     препратки
    0.43
    queles
    0.43
    Activations Density 0.006%

    No Known Activations