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. 18-GEMMASCOPE-RES-16K
    6. 8526
    Prev
    Next
    INDEX
    Explanations

    special characters and parentheses in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Abbreviations and acronyms

    np_acts-logits-general · gemini-2.0-flash

    acronyms and initialisms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     forem
    -0.43
    tac
    -0.42
    wit
    -0.40
    pop
    -0.39
    zac
    -0.38
    clang
    -0.38
     TAC
    -0.38
    TAA
    -0.37
    \]
    -0.37
     BIA
    -0.36
    POSITIVE LOGITS
     متعلقه
    0.93
     विश्वसनीयता
    0.87
     Italijani
    0.76
    intios
    0.74
    EndProject
    0.73
    RectangleBorder
    0.71
    WebServlet
    0.70
    GraphicsUnit
    0.70
     uLocal
    0.69
    enumi
    0.68
    Activations Density 0.103%

    No Known Activations