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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 12987
    Prev
    Next
    INDEX
    Explanations

    references to individuals, organizations, and governing bodies related to socio-political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Australian context or names

    np_acts-logits-general · gemini-2.0-flash

    Australian politician names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     дописавши
    -0.75
     harbour
    -0.70
     Harbour
    -0.69
     centre
    -0.65
     ujednoznacz
    -0.64
    expandindo
    -0.63
     centres
    -0.63
     realising
    -0.62
     Provincial
    -0.62
    UnsafeEnabled
    -0.61
    POSITIVE LOGITS
    hæng
    0.61
    dymyr
    0.56
     zijne
    0.55
     varandra
    0.51
     idéia
    0.51
     inalámbrica
    0.51
     hovor
    0.48
    anskje
    0.48
     enfans
    0.47
    writeFieldEnd
    0.47
    Activations Density 0.105%

    No Known Activations