© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 8342
    Prev
    Next
    INDEX
    Explanations

    references to specific terms related to the "Hor" (horizontal) classification in scientific contexts, particularly involving viruses and the associated harm or impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Begins with "Hor" or "Har"

    np_acts-logits-general · gemini-2.0-flash

    words starting with hor or har

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    APORE
    -0.72
    +#+#
    -0.72
    逅
    -0.60
    enaar
    -0.59
    Étymologie
    -0.55
    diad
    -0.54
     Serif
    -0.54
    assies
    -0.54
    hamel
    -0.53
     ddelweddau
    -0.52
    POSITIVE LOGITS
     hor
    0.70
     Hor
    0.70
    Hor
    0.69
     HOR
    0.68
    RenderAtEndOf
    0.61
    hor
    0.60
    HOR
    0.60
    })*/
    0.59
     Horacio
    0.56
    AndroidJUnit
    0.56
    Activations Density 0.079%

    No Known Activations