Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 1115
    Prev
    Next
    INDEX
    Explanations

    negative associations related to health conditions or treatments

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

    Follows hyphens, often in technical contexts

    np_acts-logits-general · gemini-2.0-flash

    fen-phen, free, graded, KOH, cross

    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
    .
    -0.64
     from
    -0.57
     in
    -0.56
     with
    -0.49
     on
    -0.48
     for
    -0.48
     is
    -0.47
     to
    -0.47
    ,
    -0.47
     of
    -0.44
    POSITIVE LOGITS
     للمعارف
    1.44
     дописавши
    1.13
    ########.
    1.07
    tvguidetime
    1.06
    
    1.04
    +#+#
    0.99
    IUrlHelper
    0.97
    GEBURTS
    0.97
    WebElementEntity
    0.96
    findpost
    0.95
    Activations Density 0.439%

    No Known Activations