© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 7182
    Prev
    Next
    INDEX
    Explanations

    references to family relationships, particularly focusing on wives and mothers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.67
     wireType
    -0.59
    transQ
    -0.58
     ब्रेकडाउन
    -0.58
     Numerade
    -0.57
     surla
    -0.57
    vician
    -0.53
     Italijanski
    -0.52
    tagHelperRunner
    -0.50
    +#+
    -0.50
    POSITIVE LOGITS
     useNavigate
    0.38
     mates
    0.38
    fjspx
    0.38
     who
    0.38
     colleagues
    0.37
    chartInstance
    0.36
    ’
    0.35
    mates
    0.34
    oldValue
    0.34
     nephews
    0.33
    Activations Density 0.265%

    No Known Activations