© 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. 14172
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their relational context in the text

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

    Sentences ending with a period

    np_acts-logits-general · gemini-2.0-flash

    listing diverse items

    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
    GOTREF
    -0.69
     subsequent
    -0.68
    WebElementEntity
    -0.65
     "..\..\..\
    -0.64
     nämlich
    -0.62
    )*/
    -0.60
     similarly
    -0.60
     Similarly
    -0.60
     secondly
    -0.59
    MessageTagHelper
    -0.59
    POSITIVE LOGITS
     allemaal
    1.25
     tudo
    1.19
     all
    1.10
    Bref
    1.08
    总之
    1.06
    这一切
    1.05
    etc
    1.05
    all
    1.02
     etc
    1.01
     semuanya
    1.00
    Activations Density 0.373%

    No Known Activations