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. 5-GEMMASCOPE-RES-16K
    6. 5159
    Prev
    Next
    INDEX
    Explanations

    references to popular series and video games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.69
    enterOuterAlt
    -0.60
    ;#
    -0.59
    InputTagHelper
    -0.56
    addGap
    -0.55
     kepad
    -0.54
    addContainerGap
    -0.53
    AddTagHelper
    -0.51
    وردار
    -0.50
    rédients
    -0.50
    POSITIVE LOGITS
     صوتيه
    0.69
     Warcraft
    0.68
     Thrones
    0.66
    gebob
    0.65
    jago
    0.64
    cipar
    0.62
    minecraft
    0.61
     sinter
    0.61
     Terraria
    0.61
    ingeki
    0.61
    Activations Density 0.283%

    No Known Activations