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. 17-GEMMASCOPE-RES-16K
    6. 7254
    Prev
    Next
    INDEX
    Explanations

    comparative phrases and concepts related to balance or contrast

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.54
     VIDEOTAPE
    -0.52
    tallet
    -0.46
     In
    -0.44
    АН
    -0.44
     dalamnya
    -0.44
    AddHtmlAttribute
    -0.42
    Hype
    -0.42
    циал
    -0.42
    дә
    -0.42
    POSITIVE LOGITS
     on
    1.62
    บน
    1.16
     trên
    1.14
     على
    1.04
     auf
    1.03
     на
    1.01
    On
    1.01
    OnThe
    0.96
     روی
    0.94
     thereon
    0.91
    Activations Density 0.395%

    No Known Activations