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. 5758
    Prev
    Next
    INDEX
    Explanations

    phrases related to authority and belief

    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
     sekaligus
    -0.38
     samym
    -0.34
    rungsseite
    -0.34
     partly
    -0.31
    partly
    -0.31
     zudem
    -0.29
     tevens
    -0.28
    一方面
    -0.28
    同时
    -0.28
    buttonShape
    -0.28
    POSITIVE LOGITS
     whatever
    4.09
    whatever
    3.77
    Whatever
    3.69
     Whatever
    3.66
     whichever
    3.27
     whoever
    2.50
     whome
    2.38
    hichever
    2.30
     wherever
    2.20
    atever
    2.02
    Activations Density 0.552%

    No Known Activations