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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6019
    Prev
    Next
    INDEX
    Explanations

    entities relevant to geographical locations and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verwijspagina
    -0.71
     autorytatywna
    -0.67
    NameInMap
    -0.58
    ſelves
    -0.57
     Verſ
    -0.57
     raiſ
    -0.57
     surla
    -0.56
    oa̍t
    -0.56
     мәкал
    -0.54
     للمعارف
    -0.53
    POSITIVE LOGITS
     doInBackground
    0.38
     report
    0.38
    Przypisy
    0.35
     جم
    0.34
     platform
    0.34
    APORE
    0.33
     --
    0.33
     package
    0.33
    nav
    0.32
     M
    0.32
    Activations Density 0.126%

    No Known Activations