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. 10-GEMMASCOPE-RES-16K
    6. 2500
    Prev
    Next
    INDEX
    Explanations

    references to government entities or functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dinah
    -0.75
     Ness
    -0.66
    itemId
    -0.65
     estoppel
    -0.65
     Missile
    -0.65
     jitter
    -0.65
     springfox
    -0.65
    イケ
    -0.64
     IgE
    -0.63
    𝒌
    -0.63
    POSITIVE LOGITS
     Government
    1.61
    Government
    1.46
     government
    1.43
     GOVERNMENT
    1.25
    GOVERNMENT
    1.24
    government
    1.22
    vernment
    1.22
     governments
    1.21
     Governments
    1.21
     governmental
    1.15
    Activations Density 0.053%

    No Known Activations