© 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. 1771
    Prev
    Next
    INDEX
    Explanations

    references to conditions or rules related to data handling or programming

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

    "that" followed by specific words

    np_acts-logits-general · gemini-2.0-flash

    note that

    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
    ValueStyle
    -0.80
    จึง
    -0.69
    extAlignment
    -0.68
     Пусть
    -0.68
    tvguidetime
    -0.65
     photolibrary
    -0.65
     tslint
    -0.64
    </caption>
    -0.64
    󠁴
    -0.63
     tuong
    -0.63
    POSITIVE LOGITS
     there
    0.92
     these
    0.86
     this
    0.81
     we
    0.69
     the
    0.68
     Unlike
    0.68
    Unlike
    0.67
     unlike
    0.67
    there
    0.66
     The
    0.64
    Activations Density 0.488%

    No Known Activations