© 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. 25-GEMMASCOPE-RES-16K
    11. 10571
    Prev
    Next
    INDEX
    Explanations

    phrases indicating steps or actions related to evaluating and improving processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.77
     propOrder
    -0.66
    SequentialGroup
    -0.65
    ConstraintMaker
    -0.64
     esternos
    -0.63
    awtextra
    -0.61
    mybatisplus
    -0.60
    featureID
    -0.58
    CDCl
    -0.58
    verwijspagina
    -0.55
    POSITIVE LOGITS
     achieve
    0.79
     smoo
    0.74
     improve
    0.74
     enhance
    0.73
     cope
    0.72
     overcome
    0.71
     attain
    0.69
     minimize
    0.68
     reduce
    0.66
     realize
    0.64
    Activations Density 0.495%

    No Known Activations