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. 7-GEMMASCOPE-RES-16K
    6. 6411
    Prev
    Next
    INDEX
    Explanations

    negations and assertions about situations or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     /\.(
    -0.53
    хьтан
    -0.52
    richtet
    -0.52
     Roskov
    -0.52
    intenant
    -0.51
    xins
    -0.50
    artificial
    -0.50
    imdi
    -0.50
    AsUp
    -0.50
    🔕
    -0.50
    POSITIVE LOGITS
     تضيفلها
    0.75
     تانيه
    0.64
    脚注の使い方
    0.63
    istoitu
    0.63
     محفوظة
    0.63
    LookAnd
    0.59
    AddHtmlAttribute
    0.59
    EndInit
    0.56
    AxisAlignment
    0.54
    ServletException
    0.54
    Activations Density 1.194%

    No Known Activations