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. 16-GEMMASCOPE-RES-16K
    6. 5075
    Prev
    Next
    INDEX
    Explanations

    phrases related to performance, evaluation, and sports statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Subjective, evaluative adjectives

    np_acts-logits-general · gemini-2.0-flash

    recent events or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     künf
    -0.70
     morrow
    -0.70
     künftig
    -0.69
    attuale
    -0.66
     tomorrow
    -0.66
     ComVisible
    -0.64
     zukünf
    -0.61
    currently
    -0.61
    ValueStyle
    -0.60
    ieteur
    -0.60
    POSITIVE LOGITS
     yesterday
    1.29
     last
    1.26
     ayer
    1.17
     earlier
    1.14
     förra
    1.12
     recently
    1.08
     damals
    1.03
    Yesterday
    0.99
    earlier
    0.97
     ontem
    0.97
    Activations Density 1.228%

    No Known Activations