© 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. 9489
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives indicating size or quality

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

    Comparative adjectives ending in "-er"

    np_acts-logits-general · gemini-2.0-flash

    comparative adjectives

    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
     High
    -0.51
    исленность
    -0.50
    RegressionTest
    -0.46
     Cross
    -0.46
     Mano
    -0.46
     Max
    -0.46
    AndEndTag
    -0.45
     Low
    -0.45
    val
    -0.44
    fromnode
    -0.44
    POSITIVE LOGITS
    Hauptartikel
    0.86
    +#+
    0.84
    )";
    0.77
     Administrativna
    0.77
    wiſe
    0.76
     Lighter
    0.76
    rungsseite
    0.76
     ſtill
    0.76
     myſelf
    0.75
     fresher
    0.75
    Activations Density 0.204%

    No Known Activations