© 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. 3-GEMMASCOPE-RES-16K
    11. 8229
    Prev
    Next
    INDEX
    Explanations

    references to the presence or absence of individuals with specific medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Begle
    -0.38
    +#+
    -0.38
     pelig
    -0.33
     neceff
    -0.33
    
    -0.33
     mourut
    -0.32
    之助
    -0.32
    RenderAtEndOf
    -0.31
    DeleteMapping
    -0.31
    Hopefully
    -0.31
    POSITIVE LOGITS
    __*/
    0.61
     betweenstory
    0.60
     którzy
    0.58
     בעל
    0.56
    stylers
    0.56
     who
    0.56
     Patients
    0.55
     possessing
    0.55
     having
    0.55
     patients
    0.52
    Activations Density 0.408%

    No Known Activations