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. 24-GEMMASCOPE-RES-16K
    6. 14192
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to magnetic phenomena and interactions at the atomic or nanoscale level

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

    "Spin" or "pseudospin" dynamics and accumulation

    np_acts-logits-general · gemini-2.0-flash

    spin dynamics accumulation coupling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    scryfall
    -0.59
     المعيارى
    -0.50
    ైన
    -0.48
    itzenden
    -0.47
    Sitemap
    -0.46
     innovate
    -0.45
    ideae
    -0.44
    ánky
    -0.44
     amorti
    -0.44
     intervening
    -0.44
    POSITIVE LOGITS
    AndEndTag
    0.80
     مشين
    0.78
    enumii
    0.73
    TypedDataSet
    0.71
    InstanceState
    0.70
     nakalista
    0.69
    ruptedException
    0.68
    出版年
    0.63
    ⓧ
    0.63
    migrationBuilder
    0.60
    Activations Density 1.231%

    No Known Activations