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-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 961
    Prev
    Next
    INDEX
    Explanations

    temporal relationships and descriptors related to days and dates

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

    temporal proximity

    np_acts-logits-general · gemini-2.0-flash

    temporal and spatial adjacency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dabei
    -0.35
    GenerationType
    -0.35
    ariado
    -0.34
    ">[
    -0.31
    tijd
    -0.31
     bl
    -0.31
     time
    -0.30
     wohl
    -0.30
     Cass
    -0.30
     endTime
    -0.29
    POSITIVE LOGITS
     виправивши
    0.71
     Biôgrafia
    0.68
     autorytatywna
    0.68
    хьтан
    0.66
    verwijspagina
    0.63
     neighbor
    0.60
    BufferException
    0.59
     Италијани
    0.59
    ніципалі
    0.58
     neighbour
    0.55
    Activations Density 0.285%

    No Known Activations