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. 8-GEMMASCOPE-RES-16K
    6. 11253
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology features and benefits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    poti
    -0.48
    jarah
    -0.45
    vodu
    -0.44
     mat
    -0.44
     localVar
    -0.44
     mengen
    -0.44
    oreo
    -0.42
    raszam
    -0.42
    ">@
    -0.42
    сек
    -0.42
    POSITIVE LOGITS
    脚注の使い方
    0.77
    sidemargin
    0.73
    bootstrapcdn
    0.67
     pungkasnya
    0.65
    Kjelder
    0.63
    Tikang
    0.63
    IsMutable
    0.63
    ulongan
    0.61
     Enjoy
    0.60
     your
    0.60
    Activations Density 0.251%

    No Known Activations