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. 15666
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "claim" and related terms

    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
    __":
    
    -0.78
    phonie
    -0.75
    التالي
    -0.74
     Oswego
    -0.73
    ibouti
    -0.70
    MatInputModule
    -0.69
    __":
    -0.69
    ckeye
    -0.69
    rsiniz
    -0.68
    artney
    -0.68
    POSITIVE LOGITS
     claims
    2.12
     Claims
    2.00
     Claim
    2.00
     claim
    1.94
     CLAIMS
    1.85
    claims
    1.80
    Claims
    1.79
    Claim
    1.79
     CLAIM
    1.77
    claim
    1.70
    Activations Density 0.099%

    No Known Activations