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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 1135
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to identity, particularly in the context of race and anonymity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    crollView
    -0.61
     հղումներ
    -0.56
    rooms
    -0.54
    bur
    -0.54
    luan
    -0.53
    room
    -0.53
    Bitch
    -0.53
    Année
    -0.52
    Room
    -0.52
     Gump
    -0.52
    POSITIVE LOGITS
     identity
    1.59
     Identity
    1.41
    identity
    1.33
     identidad
    1.29
    Identity
    1.29
     identification
    1.27
     identities
    1.26
     IDENTITY
    1.23
     Identi
    1.22
     identify
    1.21
    Activations Density 0.165%

    No Known Activations