© 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. 4762
    Prev
    Next
    INDEX
    Explanations

    code elements related to data source configuration and management

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

    Follows certain words like "Big", "user", "db", or "http"

    np_acts-logits-general · gemini-2.0-flash

    numbers or programming identifiers

    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
    ViewFeatures
    -0.70
     Majefty
    -0.66
    portál
    -0.65
     MainAxisSize
    -0.65
     InputDecoration
    -0.63
     snippetHide
    -0.61
    AndEndTag
    -0.61
     otomatig
    -0.61
    IntoConstraints
    -0.60
     myſelf
    -0.60
    POSITIVE LOGITS
     Att
    0.52
    クリル
    0.46
    щото
    0.45
     throwable
    0.44
     Bos
    0.44
    abstractmethod
    0.43
     bom
    0.42
     he
    0.41
    ellón
    0.40
     r
    0.40
    Activations Density 0.105%

    No Known Activations