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. 3383
    Prev
    Next
    INDEX
    Explanations

    references to official announcements and contracts within a business or financial context

    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
     استنادى
    -0.69
    woordig
    -0.67
    SOUNDBITE
    -0.66
     estimés
    -0.65
    hyrchwyd
    -0.59
    awtextra
    -0.58
    sendFile
    -0.55
     autorytatywna
    -0.54
     HasFactory
    -0.54
     adott
    -0.54
    POSITIVE LOGITS
     oficialmente
    0.80
     plans
    0.76
     details
    0.73
     intentions
    0.72
     preliminary
    0.66
     officiellement
    0.64
     updated
    0.63
     definitivo
    0.61
     uffic
    0.61
     results
    0.60
    Activations Density 0.464%

    No Known Activations