Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 7666
    Prev
    Next
    INDEX
    Explanations

    references to specific terms or conditions relating to legal rights and obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deſt
    -0.83
     faſt
    -0.77
     Monfieur
    -0.76
     diſt
    -0.74
     Jefus
    -0.73
     fevere
    -0.73
     ſte
    -0.72
     pleaſure
    -0.72
     raiſ
    -0.70
     uſed
    -0.70
    POSITIVE LOGITS
     such
    4.43
    such
    3.83
    Such
    3.65
     Such
    3.61
     SUCH
    3.33
     solche
    2.50
     таких
    2.27
     solchen
    2.24
     solcher
    2.19
     такие
    2.15
    Activations Density 0.202%

    No Known Activations