© 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. 2-GEMMASCOPE-RES-16K
    11. 8942
    Prev
    Next
    INDEX
    Explanations

    references to 'bear' and related terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OnInit
    -0.46
    UnsafeEnabled
    -0.45
    ⓧ
    -0.40
     Figue
    -0.39
    higan
    -0.38
    Viitteet
    -0.38
     informaci
    -0.38
     Antik
    -0.37
     CreateTagHelper
    -0.36
    sprozess
    -0.36
    POSITIVE LOGITS
     bear
    3.92
     bears
    3.45
    bear
    3.41
    Bear
    3.33
     Bear
    3.27
     bearing
    3.23
     BEAR
    3.09
    BEAR
    2.88
     Bearing
    2.86
    bears
    2.83
    Activations Density 0.190%

    No Known Activations