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. 2090
    Prev
    Next
    INDEX
    Explanations

    specific technical terminologies and phrases related to scientific research and studies

    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
     rencontre
    -0.40
     CanadaChoose
    -0.40
     esist
    -0.40
     occhiali
    -0.37
    Tikang
    -0.37
     offerte
    -0.37
     letti
    -0.37
    ✚
    -0.36
    PropertyChanging
    -0.36
     >=",
    -0.36
    POSITIVE LOGITS
     Италијани
    0.49
    ктан
    0.46
    المشاركات
    0.43
     يتيمه
    0.42
    Hentet
    0.42
    VolleyError
    0.40
    tonode
    0.38
     merito
    0.38
    utivos
    0.38
    Mobil
    0.36
    Activations Density 0.137%

    No Known Activations