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. 9609
    Prev
    Next
    INDEX
    Explanations

    phrases expressing agreement or consensus

    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
    expandindo
    -0.66
    __*/
    -0.55
     peur
    -0.53
    cadilly
    -0.52
    éb
    -0.52
    iliz
    -0.52
     BoxDecoration
    -0.51
    poc
    -0.51
    pportun
    -0.51
    quisition
    -0.51
    POSITIVE LOGITS
     Agree
    1.54
     agree
    1.49
     agreement
    1.45
     agreeing
    1.45
     disagree
    1.44
    agree
    1.39
    Agree
    1.39
     agrees
    1.34
     agreed
    1.29
     disagreed
    1.27
    Activations Density 0.349%

    No Known Activations