© 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. 14074
    Prev
    Next
    INDEX
    Explanations

    instances of the word "and" in various contexts

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

    Follows the word "that"

    np_acts-logits-general · gemini-2.0-flash

    and 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
    croll
    -0.59
    toma
    -0.55
    LLOW
    -0.49
    luğu
    -0.48
    omenclature
    -0.48
     Gio
    -0.47
    relser
    -0.46
    綽
    -0.45
    myspace
    -0.45
    mleri
    -0.43
    POSITIVE LOGITS
     that
    1.10
     وأن
    1.06
     defaultstate
    1.04
     bahwa
    1.04
     rằng
    0.94
     kwamba
    0.82
     ότι
    0.81
     bahawa
    0.79
     πως
    0.73
     dass
    0.72
    Activations Density 0.383%

    No Known Activations