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. 3-GEMMASCOPE-RES-16K
    6. 12324
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to scientific processes and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ordinaires
    -0.51
    <>();
    -0.48
    /
    -0.45
    LLocation
    -0.45
     gevonden
    -0.45
     affirmé
    -0.42
    你知道
    -0.42
     devons
    -0.42
     appartiennent
    -0.42
     partagé
    -0.41
    POSITIVE LOGITS
    Rhestr
    0.90
     Roskov
    0.88
    WithIOException
    0.88
     alphabe
    0.88
    tagHelperRunner
    0.84
    MessageTagHelper
    0.83
     beginnetje
    0.82
     Himo
    0.81
     оригіналу
    0.79
    MLLoader
    0.77
    Activations Density 4.195%

    No Known Activations