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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7868
    Prev
    Next
    INDEX
    Explanations

    file paths and directory structures in programming contexts

    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
    <tbody>
    -0.23
     leuk
    -0.21
     अध
    -0.21
     trä
    -0.21
     leva
    -0.20
    事です
    -0.19
     adop
    -0.19
    ⓘ
    -0.19
    lateinit
    -0.19
    rtype
    -0.19
    POSITIVE LOGITS
    sizeCache
    0.71
    存于互联网档案馆
    0.63
     Geſch
    0.62
    gebnissen
    0.60
     Waſſer
    0.60
    Results
    0.60
    <pad>
    0.60
    guiente
    0.60
    <unused23>
    0.59
    InputBorder
    0.59
    Activations Density 0.209%

    No Known Activations