© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 12750
    Prev
    Next
    INDEX
    Explanations

    phrases indicating insincerity or lack of substance in arguments

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

    words that convey dismissal or reduction of importance, particularly the word "mere" and related expressions like "just," "only," and "simply."

    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
     eigener
    -0.39
     langsung
    -0.38
    IntoConstraints
    -0.36
     directly
    -0.36
     directa
    -0.36
     giustizia
    -0.36
     مباشرة
    -0.36
     explí
    -0.35
     directo
    -0.35
     cielos
    -0.35
    POSITIVE LOGITS
     mere
    1.49
     merely
    1.33
    ただの
    1.12
    mere
    1.09
     Mere
    0.99
    不过是
    0.99
    Mere
    0.98
    只是一个
    0.96
     glorified
    0.83
     مجرد
    0.83
    Activations Density 0.607%

    No Known Activations