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. 8-GEMMASCOPE-RES-16K
    6. 6262
    Prev
    Next
    INDEX
    Explanations

    key phrases or statements that summarize notable situations or observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -1.05
     pylint
    -0.93
    SequentialGroup
    -0.92
     חיצוניים
    -0.89
    ,:);
    -0.87
    Datuak
    -0.87
     noqa
    -0.86
     وتسجيلات
    -0.85
    elemField
    -0.84
    '},
    
    -0.83
    POSITIVE LOGITS
    ,
    0.61
    fromnode
    0.61
    And
    0.49
     And
    0.44
    While
    0.44
     Contrary
    0.44
    Contrary
    0.42
    何より
    0.42
    us
    0.42
     betweenstory
    0.41
    Activations Density 0.353%

    No Known Activations