© 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. 2910
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and special characters that signal emotional or rhetorical emphasis

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

    Code snippets and question answering

    np_acts-logits-general · gemini-2.0-flash

    conjunctions like but

    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
    WriteTagHelper
    -0.89
     Paglinawan
    -0.71
    vignon
    -0.68
    bleshooting
    -0.67
    bootstrapcdn
    -0.66
    (""));
    -0.65
     referenties
    -0.64
    Бахар
    -0.64
    StoryboardSegue
    -0.64
    Rujuakan
    -0.63
    POSITIVE LOGITS
     And
    1.34
     but
    1.34
     and
    1.31
    And
    1.25
    But
    1.11
     But
    1.06
    Which
    1.02
     which
    1.02
    but
    1.01
     Which
    1.01
    Activations Density 0.355%

    No Known Activations