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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7-GEMMASCOPE-RES-16K
    6. 15511
    Prev
    Next
    INDEX
    Explanations

    key performance indicators or metrics in data analysis contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SqlClient
    -0.54
    ))[
    -0.54
    rollers
    -0.53
     co
    -0.51
     Chamb
    -0.51
    press
    -0.50
     McBride
    -0.50
     backup
    -0.50
    <?
    -0.48
     […]
    -0.48
    POSITIVE LOGITS
     sanitaires
    0.74
    hyrchwyd
    0.74
     DBNull
    0.71
     sanitarios
    0.70
     myſelf
    0.68
    Добавлено
    0.67
    isPresent
    0.67
     houſe
    0.67
     poffible
    0.67
     pleaſure
    0.66
    Activations Density 0.302%

    No Known Activations