© 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-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 7345
    Prev
    Next
    INDEX
    Explanations

    the term "interesting" and variations of it, indicating a focus on novelty or engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cidas
    -0.52
     démarche
    -0.51
    kson
    -0.51
     poignée
    -0.49
    erde
    -0.49
     slog
    -0.48
     Ansprüche
    -0.48
    ague
    -0.45
    odal
    -0.45
     lashes
    -0.45
    POSITIVE LOGITS
     interesting
    2.02
    interesting
    1.93
     Interesting
    1.79
    Interesting
    1.67
     fascinating
    1.41
    +#+#
    1.33
     interessante
    1.30
     intéressante
    1.22
     interesante
    1.21
     intéressant
    1.21
    Activations Density 0.067%

    No Known Activations