© 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. 14776
    Prev
    Next
    INDEX
    Explanations

    references to popular television shows and their cultural impact

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

    TV shows and seasons

    np_acts-logits-general · gemini-2.0-flash

    TV series and shows

    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
    ništvo
    -0.59
    lwjgl
    -0.59
    SneakyThrows
    -0.47
     istore
    -0.46
     seclusion
    -0.45
     legible
    -0.45
     PBT
    -0.44
     CreateTagHelper
    -0.44
     deposits
    -0.44
     ultrasonic
    -0.43
    POSITIVE LOGITS
     Season
    1.36
     season
    1.33
    Season
    1.20
     episodes
    1.18
     series
    1.18
     TV
    1.14
    season
    1.14
     seasons
    1.14
     tv
    1.06
     television
    1.06
    Activations Density 0.461%

    No Known Activations