© 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. 18-GEMMASCOPE-RES-16K
    11. 8988
    Prev
    Next
    INDEX
    Explanations

    obtuse references and structured data elements in a code-like format

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

    Swift protobuf code

    np_acts-logits-general · gemini-2.0-flash

    change in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftagPool
    -0.67
    TProtocol
    -0.64
    bufio
    -0.61
     isKindOfClass
    -0.56
    bootstrapcdn
    -0.55
    AutoScaleMode
    -0.53
    openConnection
    -0.53
    PreferredItem
    -0.52
    WriteTagHelper
    -0.52
    AnimationsModule
    -0.51
    POSITIVE LOGITS
     nakalista
    0.66
    TagMode
    0.64
    èdia
    0.64
    Diweddarwch
    0.62
     nahilalakip
    0.59
    NameInMap
    0.57
     poros
    0.54
    extAlignment
    0.54
    onomía
    0.53
    richTextPanel
    0.53
    Activations Density 0.042%

    No Known Activations