Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 5851
    Prev
    Next
    INDEX
    Explanations

    references to family and familial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ActionCreators
    -0.58
     Hadrian
    -0.46
     vector
    -0.46
     HttpNotFound
    -0.45
    PMailer
    -0.45
     RSSSF
    -0.44
     quæ
    -0.44
     Perſ
    -0.42
     IndexPath
    -0.42
     resistivity
    -0.41
    POSITIVE LOGITS
     reality
    0.75
     Reality
    0.67
    Reality
    0.64
    reality
    0.64
     Housewives
    0.56
     Bravo
    0.56
     Vander
    0.54
     housewives
    0.51
     housewife
    0.49
    alité
    0.47
    Activations Density 0.170%

    No Known Activations