© 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. 257
    Prev
    Next
    INDEX
    Explanations

    references to organizations and their activities, particularly those related to meetings, events, and community engagement

    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
    upaten
    -0.52
     EClass
    -0.49
    ThemeOverlay
    -0.48
    MessageTagHelper
    -0.48
    setVerticalGroup
    -0.47
    васто
    -0.47
    asjoner
    -0.47
    kháu
    -0.45
    forKey
    -0.45
    standen
    -0.44
    POSITIVE LOGITS
     host
    1.50
     hold
    1.49
     hosting
    1.35
     holding
    1.34
     hosts
    1.29
     holds
    1.24
    hold
    1.24
    host
    1.23
     Hold
    1.21
     held
    1.20
    Activations Density 0.315%

    No Known Activations