© 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. 4-GEMMASCOPE-RES-16K
    6. 12725
    Prev
    Next
    INDEX
    Explanations

    segments of text containing formatting or structural elements, particularly around quotes or document structure markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArrowToggle
    -0.89
    aarrggbb
    -0.86
    fromnode
    -0.85
     propOrder
    -0.82
    RegressionTest
    -0.80
    rungsseite
    -0.78
     Commencez
    -0.77
     tjän
    -0.75
    GEBURTSDATUM
    -0.73
    })`
    -0.73
    POSITIVE LOGITS
     S
    0.61
     A
    0.60
     K
    0.57
     C
    0.57
     I
    0.57
    nhung
    0.56
     D
    0.55
     E
    0.55
     N
    0.53
    sprach
    0.52
    Activations Density 0.203%

    No Known Activations