© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3409
    Prev
    Next
    INDEX
    Explanations

    phrases related to absolute qualities or completeness

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

    words and phrases that complete the structure "all [you/it/...]" or similar quantifier expressions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.47
    Everyone
    -0.45
     iedereen
    -0.41
     Everyone
    -0.40
     overal
    -0.36
    bular
    -0.35
     gesamte
    -0.34
    Everybody
    -0.34
     jedem
    -0.34
     Everybody
    -0.33
    POSITIVE LOGITS
     all
    2.09
     все
    1.20
    all
    1.16
     semua
    0.97
     kaikki
    0.89
    All
    0.87
     ALL
    0.82
     All
    0.82
     همه
    0.77
     всё
    0.77
    Activations Density 0.242%

    No Known Activations