© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 5357
    Prev
    Next
    INDEX
    Explanations

    dialogs and speech-related phrases

    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
    TagMode
    -0.64
    sidemargin
    -0.57
     BorderRadius
    -0.55
     تضيفلها
    -0.53
    BeginContext
    -0.53
    WriteAttribute
    -0.53
    Cyfeiriadau
    -0.52
    Normdaten
    -0.51
    DockStyle
    -0.51
    uxxxx
    -0.50
    POSITIVE LOGITS
     muttered
    0.83
     draw
    0.82
     murmured
    0.77
    draw
    0.71
     cro
    0.71
     mumbled
    0.70
     mut
    0.70
     exclaimed
    0.69
     announced
    0.68
     whispered
    0.67
    Activations Density 0.142%

    No Known Activations