© 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-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 8974
    Prev
    Next
    INDEX
    Explanations

    references to family or familial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -0.94
    expandindo
    -0.88
     iſt
    -0.86
     Efq
    -0.85
     mourut
    -0.84
     feroit
    -0.82
     avoient
    -0.79
     boire
    -0.78
     photolibrary
    -0.77
     pleaſure
    -0.76
    POSITIVE LOGITS
     families
    1.03
     Families
    0.89
    families
    0.79
    Families
    0.79
     familles
    0.74
     familias
    0.72
     referenties
    0.63
     extra
    0.61
     last
    0.58
    Famille
    0.56
    Activations Density 0.175%

    No Known Activations