© 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-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 2209
    Prev
    Next
    INDEX
    Explanations

    expressions of affection and compliments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BufferException
    -0.54
    bootstrapcdn
    -0.45
    ponses
    -0.43
     Perſ
    -0.43
     Verdi
    -0.42
     Dryden
    -0.40
     ſta
    -0.40
    IntoConstraints
    -0.40
    principalTable
    -0.40
    cobra
    -0.40
    POSITIVE LOGITS
     cute
    2.03
     adorable
    1.84
     cutest
    1.77
     Cute
    1.76
    Cute
    1.70
    cute
    1.66
     Adorable
    1.60
     CUTE
    1.55
    Adorable
    1.55
    adorable
    1.44
    Activations Density 0.225%

    No Known Activations