© 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. 37-GEMMASCOPE-RES-16K
    11. 5028
    Prev
    Next
    INDEX
    Explanations

    expressions of impact or significance, particularly related to the word "hit."

    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
    Географија
    -0.39
    
    -0.34
     births
    -0.34
    MemoryWarning
    -0.33
    JoinColumn
    -0.32
    izr
    -0.32
    __":
    -0.31
     termica
    -0.31
     dost
    -0.31
     tillegg
    -0.31
    POSITIVE LOGITS
     hardest
    0.84
     harder
    0.76
     hard
    0.75
     jackpot
    0.74
     HARD
    0.68
    HARD
    0.67
    hard
    0.65
    ched
    0.65
     squarely
    0.62
     reset
    0.57
    Activations Density 0.195%

    No Known Activations