© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 8340
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and personal history

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     noDo
    -0.57
    avajillas
    -0.57
    <bos>
    -0.46
    ganu
    -0.45
     rå
    -0.44
     (!_
    -0.43
     or
    -0.42
     Mather
    -0.42
    seers
    -0.42
    rimir
    -0.41
    POSITIVE LOGITS
    ScopeManager
    0.72
     تانيه
    0.71
     pinulongan
    0.71
    
    0.69
    UnitTesting
    0.68
    SBATCH
    0.68
    ollectionView
    0.66
     صوتيه
    0.65
    Попис
    0.64
    contentLoaded
    0.62
    Activations Density 0.081%

    No Known Activations