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. 7-GEMMASCOPE-RES-16K
    6. 14917
    Prev
    Next
    INDEX
    Explanations

    transitions and contrasts in argumentation or narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.67
     referenties
    -0.65
     Litu
    -0.60
    Mű
    -0.58
    Дереккөздер
    -0.58
     Croydon
    -0.57
    zeera
    -0.57
     Hendrix
    -0.56
     Renaud
    -0.56
    انتهای
    -0.55
    POSITIVE LOGITS
     But
    1.67
     but
    1.57
    But
    1.54
    but
    1.43
     BUT
    1.33
     pero
    1.31
     yet
    1.19
    BUT
    1.18
     nhưng
    1.18
    但这
    1.15
    Activations Density 0.403%

    No Known Activations