© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2760
    Prev
    Next
    INDEX
    Explanations

    references to ground states or conditions in various contexts

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

    "ground" followed by "state"

    np_acts-logits-general · gemini-2.0-flash

    ground state or ground truth

    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
    ⓧ
    -0.78
     CreateTagHelper
    -0.69
    httphttps
    -0.64
     AssemblyCulture
    -0.60
    裟
    -0.60
    expandindo
    -0.59
     للمعارف
    -0.59
     Vicenza
    -0.58
     Cull
    -0.56
    esity
    -0.56
    POSITIVE LOGITS
     Ground
    0.85
    Ground
    0.84
     GROUND
    0.83
    GROUND
    0.78
    swell
    0.76
    ground
    0.76
     ground
    0.76
     floor
    0.69
    Grind
    0.68
    grou
    0.67
    Activations Density 0.087%

    No Known Activations