© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 11998
    Prev
    Next
    INDEX
    Explanations

    references to animals and animal-related topics, particularly in research and ethics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.53
     eens
    -0.53
    rrggbb
    -0.51
    Rewrite
    -0.50
    /*!
    -0.49
    mergeFrom
    -0.48
     drenched
    -0.48
     kdy
    -0.46
     Documentation
    -0.46
     rewritten
    -0.45
    POSITIVE LOGITS
     Animals
    1.15
     animals
    1.11
     Animal
    1.10
    Animal
    1.10
     animal
    1.09
    Animals
    1.09
    animals
    1.06
     ANIMALS
    1.05
     ANIMAL
    1.02
    ANIMAL
    1.01
    Activations Density 0.169%

    No Known Activations