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. 21-GEMMASCOPE-RES-16K
    6. 8454
    Prev
    Next
    INDEX
    Explanations

    references to Ethiopia and its cultural or artistic elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    trus
    -0.55
     Orrell
    -0.53
    ⁢
    -0.51
     Isle
    -0.49
     Paco
    -0.48
     Antilles
    -0.48
    venez
    -0.47
    tabria
    -0.46
    >)</
    -0.45
    FieldName
    -0.45
    POSITIVE LOGITS
     Ethiopian
    1.10
     Ethiopia
    1.06
     Addis
    0.95
    Ethio
    0.94
     Ethio
    0.90
    Ethiopia
    0.88
     Debre
    0.70
     Erit
    0.70
     Tig
    0.69
     Eritrea
    0.68
    Activations Density 0.036%

    No Known Activations