© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 2614
    Prev
    Next
    INDEX
    Explanations

    numerical values and punctuation in technical or mathematical contexts

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

    Punctuation after citations or URLs

    np_acts-logits-general · gemini-2.0-flash

    lund et al / reducing post-operative

    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
     whatever
    -0.59
     وتسجيلات
    -0.55
    ghis
    -0.55
    xtext
    -0.52
    oldt
    -0.51
    ℗
    -0.51
    ésult
    -0.49
    |}{$
    -0.49
     push
    -0.49
    ngdoc
    -0.48
    POSITIVE LOGITS
    ↵↵
    0.89
    <eos>
    0.85
     kasarigan
    0.70
    ↵
    0.70
    }`).
    0.67
     Also
    0.65
     Roskov
    0.65
     reprinted
    0.63
     ویکی‌پدی
    0.61
    Also
    0.60
    Activations Density 0.160%

    No Known Activations