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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13067
    Prev
    Next
    INDEX
    Explanations

    terms related to medical and scientific research, particularly in genetics and pathology

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

    followed by numbers

    np_acts-logits-general · gemini-2.0-flash

    rectal or feed company

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.62
    setVerticalGroup
    -0.60
    хьтан
    -0.60
    MLLoader
    -0.54
    EndContext
    -0.54
    bootstrapcdn
    -0.52
     Normdatei
    -0.51
    lusconi
    -0.50
    styleType
    -0.50
     contextLoads
    -0.50
    POSITIVE LOGITS
    Parcelize
    0.46
    LookAnd
    0.46
    addCriterion
    0.42
     hObject
    0.41
     الاطلاع
    0.37
     cứ
    0.36
    ứ
    0.35
    }}^{(
    0.35
    ioutil
    0.34
    مراجع
    0.33
    Activations Density 1.744%

    No Known Activations