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. 1692
    Prev
    Next
    INDEX
    Explanations

    descriptions of local culture and culinary offerings

    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
     inoxydable
    -0.58
     pauvres
    -0.56
     mijne
    -0.55
    ANDUM
    -0.55
     bezeichneter
    -0.54
    uerdo
    -0.54
     enfans
    -0.53
    ็จ
    -0.51
     BoxFit
    -0.51
     combien
    -0.51
    POSITIVE LOGITS
     goodness
    0.94
     delights
    0.84
     vibes
    0.79
     fare
    0.77
     pleasures
    0.76
     favorites
    0.75
     favourites
    0.74
     treasures
    0.72
     adventures
    0.72
     perfection
    0.72
    Activations Density 0.243%

    No Known Activations