© 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. 8-GEMMASCOPE-RES-16K
    11. 11101
    Prev
    Next
    INDEX
    Explanations

    probable outcomes or assertions throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Z
    -0.51
     miten
    -0.50
     Ches
    -0.49
     movimentos
    -0.49
    CHM
    -0.49
     resultSet
    -0.48
     élevées
    -0.48
    inander
    -0.48
     dance
    -0.48
    orme
    -0.47
    POSITIVE LOGITS
     Probably
    1.48
     probably
    1.44
    Probably
    1.33
    bably
    1.32
     prolly
    1.32
    probably
    1.28
     likely
    1.18
     perhaps
    1.12
     Likely
    1.12
     Perhaps
    1.05
    Activations Density 0.090%

    No Known Activations