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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12849
    Prev
    Next
    INDEX
    Explanations

    references to time periods, particularly focusing on the past and future

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

    "past" and related concepts

    np_acts-logits-general · gemini-2.0-flash

    past and future

    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
     CDP
    -0.69
    glio
    -0.69
     Gideon
    -0.69
     purpoſe
    -0.67
    rokken
    -0.64
     Garibaldi
    -0.64
     Johnnie
    -0.64
     découv
    -0.64
     følge
    -0.63
     Assignee
    -0.63
    POSITIVE LOGITS
     Past
    1.43
    Past
    1.33
     past
    1.29
     PAST
    1.20
    past
    1.17
    PAST
    1.11
     tense
    0.82
    StoryboardSegue
    0.73
     Pas
    0.70
     passato
    0.67
    Activations Density 0.072%

    No Known Activations