© 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-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 4235
    Prev
    Next
    INDEX
    Explanations

    references to authority and justification within religious contexts

    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
     JpaRepository
    -0.53
    DispatchToProps
    -0.52
     للاسماء
    -0.52
    хьтан
    -0.52
    OGND
    -0.50
    QMetaType
    -0.50
     Propiedad
    -0.49
     gyhoeddwyd
    -0.48
     Numerade
    -0.48
    LEncoder
    -0.48
    POSITIVE LOGITS
     sin
    0.68
     worldly
    0.68
     carnal
    0.58
     idolat
    0.54
     pagan
    0.54
     sinful
    0.53
     Sünde
    0.53
     idol
    0.51
     false
    0.50
     secular
    0.50
    Activations Density 0.386%

    No Known Activations