© 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. 9264
    Prev
    Next
    INDEX
    Explanations

    special characters and various types of brackets and parentheses in the text

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

    Opening parenthesis followed by math symbols

    np_acts-logits-general · gemini-2.0-flash

    academic paper structure

    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
    edig
    -0.46
    <eos>
    -0.45
     sí
    -0.43
     roll
    -0.42
    iVar
    -0.41
     []:
    -0.40
    yti
    -0.39
    bru
    -0.39
    ModelSerializer
    -0.39
     truk
    -0.39
    POSITIVE LOGITS
     invokingState
    0.84
     Савезне
    0.76
     виправивши
    0.74
    XmlAccessorType
    0.70
    NameInMap
    0.68
     fhew
    0.68
     endregion
    0.68
    antaranya
    0.66
     mukana
    0.65
    wpi
    0.65
    Activations Density 0.144%

    No Known Activations