© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 3893
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to groups of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.73
     InputDecoration
    -0.70
    IsMutable
    -0.67
    niſſe
    -0.64
    pushFollow
    -0.63
    ⤒
    -0.62
    featureID
    -0.62
    İstinadlar
    -0.61
     zwiſchen
    -0.59
    adaptiveStyles
    -0.58
    POSITIVE LOGITS
     guys
    0.47
     folks
    0.40
     Feldman
    0.38
    uanya
    0.37
     ones
    0.37
     people
    0.36
    <bos>
    0.36
     guy
    0.35
     part
    0.35
    fla
    0.35
    Activations Density 0.186%

    No Known Activations