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. 20-GEMMASCOPE-RES-16K
    6. 5008
    Prev
    Next
    INDEX
    Explanations

    references to albums and their release details

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

    Preceding ordinal numbers referring to albums

    np_acts-logits-general · gemini-2.0-flash

    album release information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     linkovi
    -0.71
    Демографія
    -0.63
    MessageState
    -0.62
     numberWith
    -0.62
    providedIn
    -0.61
     corrector
    -0.60
    بوابة
    -0.57
    ViewStyle
    -0.56
    }")]
    -0.55
    Cele
    -0.54
    POSITIVE LOGITS
     album
    1.40
     albums
    1.13
    album
    1.04
     Album
    1.00
     EP
    0.94
     ALBUM
    0.92
     álbum
    0.91
    Album
    0.90
     альбо
    0.84
     альбом
    0.84
    Activations Density 0.123%

    No Known Activations