© 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. 8321
    Prev
    Next
    INDEX
    Explanations

    gerunds and present participles in various contexts

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

    ending in "-ing" that start a clause

    np_acts-logits-general · gemini-2.0-flash

    `getting` and `looking` verbs

    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
    fikasi
    -0.71
    rsiniz
    -0.70
    setopt
    -0.59
    endphp
    -0.54
     Folge
    -0.53
    kå
    -0.53
    stości
    -0.52
    illoma
    -0.52
    <%=
    -0.52
    後は
    -0.51
    POSITIVE LOGITS
    gggg
    0.98
    ly
    0.92
    parsedMessage
    0.86
    ggg
    0.86
    Билгалдахарш
    0.84
    ging
    0.77
    ting
    0.76
    GEBURTSDATUM
    0.73
     Meksiku
    0.72
    GGGG
    0.72
    Activations Density 0.292%

    No Known Activations