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-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16054
    Prev
    Next
    INDEX
    Explanations

    references to gaming consoles and related hardware

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

    Video game consoles

    np_acts-logits-general · gemini-2.0-flash

    video game consoles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ITF
    -0.42
     sombras
    -0.38
     beroep
    -0.38
    VOA
    -0.38
    AMBI
    -0.38
    点此举报
    -0.38
    MNA
    -0.37
     zelve
    -0.37
    fiore
    -0.37
     Ausdrücke
    -0.36
    POSITIVE LOGITS
     consoles
    0.93
     console
    0.92
     Console
    0.74
    MessageTagHelper
    0.71
     Xbox
    0.69
    Console
    0.66
     consola
    0.66
    console
    0.60
     xbox
    0.58
    ValueStyle
    0.58
    Activations Density 0.048%

    No Known Activations