© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 2930
    Prev
    Next
    INDEX
    Explanations

    results and conclusions related to scientific studies or papers

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

    "5" followed by a non-numerical character

    np_acts-logits-general · gemini-2.0-flash

    numbers following 5

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dabar
    -0.51
     spesa
    -0.51
    liesslich
    -0.49
     profondità
    -0.49
     tenisky
    -0.49
    četně
    -0.49
    DeleteBehavior
    -0.49
     déchir
    -0.48
    regas
    -0.47
    ckså
    -0.47
    POSITIVE LOGITS
     חיצוניים
    0.75
    uxxxx
    0.63
    хьтан
    0.62
    IContainer
    0.60
    isesi
    0.60
     arşivlendi
    0.59
    TestingModule
    0.58
    ########.
    0.58
    SequentialGroup
    0.58
    ]]:
    0.56
    Activations Density 0.105%

    No Known Activations