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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 12903
    Prev
    Next
    INDEX
    Explanations

    negative indicators or symbols denoting absence or negation

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

    Text near mathematical or numerical symbols

    np_acts-logits-general · gemini-2.0-flash

    reversed during reperfusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ddelweddau
    -0.74
    Билгалдахарш
    -0.71
    ">—
    -0.70
     مشين
    -0.68
    SourceChecksum
    -0.68
    bukkit
    -0.68
     חיצוניים
    -0.67
    ValueStyle
    -0.67
     saites
    -0.66
    AndEndTag
    -0.66
    POSITIVE LOGITS
     كومونز
    0.67
     peine
    0.54
     depending
    0.51
    depending
    0.48
    awtextra
    0.45
    zegor
    0.45
     voire
    0.44
    ishly
    0.44
    nictví
    0.42
     quizás
    0.42
    Activations Density 0.244%

    No Known Activations