© 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. 12-GEMMASCOPE-RES-16K
    6. 14991
    Prev
    Next
    INDEX
    Explanations

    negative phrases or expressions of doubt and uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.54
    ksp
    -0.50
    ERICK
    -0.49
     ….
    -0.48
    ActionResult
    -0.48
     AssemblyTitle
    -0.47
    fortawesome
    -0.47
    بوابة
    -0.46
     ……
    -0.46
     indisponible
    -0.46
    POSITIVE LOGITS
     dAtA
    0.67
     öyle
    0.59
     cerevisiae
    0.53
    ThemeOverlay
    0.52
     OMITBAD
    0.51
    IsContent
    0.51
     farlo
    0.50
     solche
    0.50
     Böyle
    0.50
     white
    0.49
    Activations Density 0.844%

    No Known Activations