Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 14958
    Prev
    Next
    INDEX
    Explanations

    words related to identity, particularly personal pronouns and names

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

    French "Je" and related conjugations

    np_acts-logits-general · gemini-2.0-flash

    French phrases beginning with Je

    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
    Personendaten
    -1.15
    脚注の使い方
    -0.89
    UnusedPrivate
    -0.82
    DockStyle
    -0.78
    rungsseite
    -0.77
    发表于
    -0.77
     disambiguazione
    -0.76
     FishBase
    -0.75
     insuffisamment
    -0.74
     Wallflower
    -0.74
    POSITIVE LOGITS
     Jez
    0.71
     Je
    0.67
    Je
    0.64
    jee
    0.55
    JEE
    0.53
    je
    0.52
    getc
    0.52
    noinspection
    0.50
     Jeffer
    0.49
    jeti
    0.47
    Activations Density 0.127%

    No Known Activations