© 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. 4-GEMMASCOPE-RES-16K
    11. 2814
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to quantum mechanics and probability theory

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]='\
    -0.80
    🏾
    -0.61
     CreateTagHelper
    -0.61
    orghini
    -0.57
     berdua
    -0.56
    JspWriter
    -0.55
     Générale
    -0.54
     CGSize
    -0.54
     gynhyrchwyd
    -0.54
    anship
    -0.54
    POSITIVE LOGITS
    bitset
    0.58
    OrBuilder
    0.56
    classnames
    0.56
    Демографія
    0.55
    oulli
    0.53
     binomial
    0.52
    Становништво
    0.52
    ManyToMany
    0.50
    migrationBuilder
    0.48
    rrggbb
    0.47
    Activations Density 2.146%

    No Known Activations