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. 31-GEMMASCOPE-RES-16K
    6. 16247
    Prev
    Next
    INDEX
    Explanations

    words related to personal experiences and relationships

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

    followed by past-participle verbs

    np_acts-logits-general · gemini-2.0-flash

    we get, I remember, they follow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ьаж
    -0.78
     فريبيس
    -0.58
    rrggbb
    -0.54
    antMatchers
    -0.53
    IsContent
    -0.52
     autorytatywna
    -0.52
    rxjs
    -0.52
     pinulongan
    -0.51
    RequestParam
    -0.51
     AssemblyCulture
    -0.51
    POSITIVE LOGITS
    عنی
    0.37
     FontWeight
    0.34
     обо
    0.34
     
    0.31
    Показать
    0.31
    ഊ
    0.30
     bezeichneter
    0.30
    URATION
    0.30
     nou
    0.30
    -------
    0.30
    Activations Density 0.647%

    No Known Activations