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. 8-GEMMASCOPE-RES-16K
    6. 5782
    Prev
    Next
    INDEX
    Explanations

    instances of the word "out" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bohn
    -0.57
     Lad
    -0.57
    齡
    -0.57
    antana
    -0.57
    ocha
    -0.57
     zbo
    -0.57
    trusted
    -0.56
     trusted
    -0.56
     Cowley
    -0.56
    ={`${
    -0.56
    POSITIVE LOGITS
    RectangleBorder
    0.84
     layui
    0.77
     itſelf
    0.71
     nawr
    0.68
     heraus
    0.68
    روج
    0.68
     الحره
    0.66
     BnF
    0.65
     unsc
    0.65
    ýš
    0.64
    Activations Density 0.124%

    No Known Activations