© 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. 3-GEMMASCOPE-RES-16K
    11. 13154
    Prev
    Next
    INDEX
    Explanations

    terms and phrases indicating neutrality or a lack of bias

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.85
     devenus
    -0.77
     sanguí
    -0.72
     rencont
    -0.71
     africains
    -0.69
     Advancement
    -0.69
     Complexity
    -0.68
    loem
    -0.68
    примеча
    -0.68
    ActionCreators
    -0.67
    POSITIVE LOGITS
     neutral
    3.62
     Neutral
    3.26
    neutral
    3.18
    Neutral
    3.13
    UTRAL
    2.69
     neutr
    2.58
     нейтра
    2.52
     neutrality
    2.51
     neutrals
    2.50
     neutre
    2.40
    Activations Density 0.103%

    No Known Activations