© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8759
    Prev
    Next
    INDEX
    Explanations

    references to daily life and generational transmission of skills

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 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
     CreateTagHelper
    -0.48
    μβρίου
    -0.47
    ecake
    -0.46
    原始内容存档
    -0.46
    Conver
    -0.42
    Lieu
    -0.42
     Plut
    -0.42
    mption
    -0.42
     Conver
    -0.41
    elum
    -0.41
    POSITIVE LOGITS
     daily
    0.48
    ToLeft
    0.45
    lijkse
    0.43
    每日
    0.42
    Daily
    0.40
     vectorielle
    0.39
    々と
    0.39
     Daily
    0.39
     everyday
    0.38
    Enllaços
    0.38
    Activations Density 0.329%

    No Known Activations