© 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. 9598
    Prev
    Next
    INDEX
    Explanations

    phrases indicating recent time periods

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

    "recent years" and following time units

    np_acts-logits-general · gemini-2.0-flash

    recent time units

    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
    esercito
    -0.49
    TagHelpers
    -0.45
    AlterField
    -0.43
     InputDecoration
    -0.41
     once
    -0.41
     Reverso
    -0.39
    quiera
    -0.39
     verschillen
    -0.39
     dry
    -0.38
    twice
    -0.38
    POSITIVE LOGITS
     years
    1.83
     weeks
    1.66
     months
    1.61
    years
    1.45
     days
    1.44
    Years
    1.32
    months
    1.30
    weeks
    1.29
     YEARS
    1.27
     decades
    1.26
    Activations Density 0.152%

    No Known Activations