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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 4455
    Prev
    Next
    INDEX
    Explanations

    data related to financial metrics and statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.53
    mode
    -0.49
     καν
    -0.48
    freies
    -0.46
    its
    -0.45
    TH
    -0.45
    КТ
    -0.44
    th
    -0.43
    biz
    -0.43
    연
    -0.43
    POSITIVE LOGITS
     typelib
    0.77
    HideFlags
    0.77
    IntoConstraints
    0.73
    Personensuche
    0.72
    utilisons
    0.72
     صوتيه
    0.72
    BeginInit
    0.72
    पया
    0.71
    <?
    0.70
    EndGlobalSection
    0.70
    Activations Density 0.141%

    No Known Activations