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. 14940
    Prev
    Next
    INDEX
    Explanations

    instances of the word "all" and its variations suggesting completeness or totality

    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
     Ferne
    -0.79
    ➜
    -0.71
    er
    -0.70
    Viki
    -0.70
     Moskva
    -0.69
    jstor
    -0.69
     Ayu
    -0.68
    sierten
    -0.66
     Napier
    -0.66
    Programme
    -0.66
    POSITIVE LOGITS
     all
    1.60
     ALL
    1.55
     All
    1.40
    All
    1.34
    ALL
    1.25
    ReadAll
    1.24
     deleteAll
    1.23
    all
    1.22
     GetAll
    1.18
    setAll
    1.13
    Activations Density 0.183%

    No Known Activations