© 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. 8-GEMMASCOPE-RES-16K
    11. 7760
    Prev
    Next
    INDEX
    Explanations

    terms related to support and endorsements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hauptartikel
    -0.59
    achet
    -0.47
     Roskov
    -0.42
    してしまった
    -0.42
    owę
    -0.41
    存于互联网档案馆
    -0.40
    stree
    -0.37
    utica
    -0.36
    modelBuilder
    -0.36
     hộ
    -0.36
    POSITIVE LOGITS
    PasswordEncoder
    0.72
    AndEndTag
    0.71
    SBATCH
    0.71
     ſever
    0.69
    httphttps
    0.69
    Ecotoxicity
    0.68
    الحياه
    0.67
     unanimous
    0.66
     fevere
    0.65
     Majefty
    0.64
    Activations Density 0.441%

    No Known Activations