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. 10-GEMMASCOPE-RES-16K
    6. 4461
    Prev
    Next
    INDEX
    Explanations

    proper names and notable individuals related to politics, entertainment, and sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPJ
    -0.61
    ilibrium
    -0.58
     memberId
    -0.57
    (::
    -0.56
    новништво
    -0.54
    yntax
    -0.53
    település
    -0.51
     Lub
    -0.51
    )}</
    -0.51
    gnition
    -0.51
    POSITIVE LOGITS
    featureID
    0.88
    AndEndTag
    0.74
     Shakira
    0.72
    ukone
    0.67
    Obama
    0.66
    ttino
    0.64
    LookAnd
    0.64
    NewGuid
    0.63
     Obama
    0.62
    rovnik
    0.62
    Activations Density 0.229%

    No Known Activations