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. 9-GEMMASCOPE-RES-16K
    6. 3365
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to XML schemas

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

    XML namespace declarations

    np_acts-logits-general · gemini-2.0-flash

    XML namespaces and URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PeEnEo
    -0.64
    leſs
    -0.59
    ſelf
    -0.55
    enderror
    -0.54
    tonode
    -0.53
     Reſ
    -0.52
    WireFormatLite
    -0.52
    SharedDtor
    -0.51
    ſelves
    -0.51
    bibfield
    -0.49
    POSITIVE LOGITS
     nahilalakip
    0.38
     незавершена
    0.34
    CrossRef
    0.34
    Kaynakça
    0.34
    Spirit
    0.33
    AddTagHelper
    0.33
    Lähteet
    0.33
    legislation
    0.32
     spirit
    0.32
     Roskov
    0.31
    Activations Density 0.592%

    No Known Activations