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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 6395
    Prev
    Next
    INDEX
    Explanations

    terms related to the word "state"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cherchés
    -0.79
    EndProject
    -0.78
    脚注の使い方
    -0.76
     صوتيه
    -0.72
     CreateTagHelper
    -0.72
    fromnode
    -0.72
    Біографія
    -0.71
    ModelSerializer
    -0.70
    ьаж
    -0.70
    entric
    -0.70
    POSITIVE LOGITS
     Sta
    1.82
     sta
    1.75
    Sta
    1.60
    stap
    1.29
     Staple
    1.05
     ста
    1.04
    sta
    1.03
     staple
    0.94
    Ста
    0.93
     Ста
    0.85
    Activations Density 0.063%

    No Known Activations