© 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. 16-GEMMASCOPE-RES-16K
    11. 5509
    Prev
    Next
    INDEX
    Explanations

    terms related to the act of releasing or issuing something

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

    "release" or "released"

    np_acts-logits-general · gemini-2.0-flash

    release

    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
     pharmacie
    -0.59
     Geno
    -0.57
     Cotter
    -0.57
    ाई
    -0.57
     CARD
    -0.51
     krop
    -0.51
     card
    -0.50
     Wys
    -0.50
     Card
    -0.50
    ceptors
    -0.49
    POSITIVE LOGITS
     releases
    1.54
     release
    1.53
     Release
    1.52
     Releases
    1.51
     RELEASE
    1.43
    Release
    1.40
    release
    1.35
    RELEASE
    1.35
    Releases
    1.29
     releasing
    1.25
    Activations Density 0.147%

    No Known Activations