© 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. 39-GEMMASCOPE-RES-16K
    11. 3278
    Prev
    Next
    INDEX
    Explanations

    mentions of shark-related encounters or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     springfox
    -0.46
     Ravenna
    -0.42
    TemporalType
    -0.41
    FirstResponder
    -0.41
     rabbits
    -0.41
     transfieras
    -0.40
     AspNetCore
    -0.40
    badlogic
    -0.40
     Rabbits
    -0.39
     beetles
    -0.39
    POSITIVE LOGITS
     whale
    1.43
     whales
    1.31
     Whale
    1.19
    whale
    1.14
    Whale
    1.13
     Whales
    1.09
     hump
    0.96
     dolphins
    0.92
     dolphin
    0.91
     shark
    0.87
    Activations Density 0.305%

    No Known Activations