© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14780
    Prev
    Next
    INDEX
    Explanations

    terms that indicate relative measurements or comparisons

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

    words using the -tive family of suffixes (e.g., -tive, -tivity, -atively/-ively).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "relative" or "objective" in formal scientific or technical writing.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Irán
    -0.71
    ltä
    -0.61
     Inscrivez
    -0.56
     Teléfono
    -0.56
     voici
    -0.54
     čaj
    -0.53
    føring
    -0.52
     Söz
    -0.52
    Semoga
    -0.50
    éndolo
    -0.50
    POSITIVE LOGITS
    tive
    0.84
    itive
    0.80
    estive
    0.79
    ative
    0.79
    sive
    0.77
    ressive
    0.77
    ulative
    0.76
    lective
    0.74
    ensive
    0.72
    perative
    0.71
    Activations Density 0.223%

    No Known Activations