© 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. 4102
    Prev
    Next
    INDEX
    Explanations

    terms related to artistic or historical context

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

    that can precede a colon

    np_acts-logits-general · gemini-2.0-flash

    dread, legislation, significant

    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
    非常的
    -1.11
     می‌باشد
    -0.89
    十分的
    -0.87
    很多的
    -0.86
     dimana
    -0.85
     данного
    -0.79
     didalam
    -0.79
    慢慢的
    -0.77
     poichè
    -0.77
    の為
    -0.77
    POSITIVE LOGITS
     freilich
    1.05
    —“
    1.00
     disambiguazione
    0.98
    TagMode
    0.93
    —"
    0.92
    —
    0.90
    ​—
    0.90
    —”
    0.90
    WebElementEntity
    0.88
     едва
    0.86
    Activations Density 1.536%

    No Known Activations