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. 15-GEMMASCOPE-RES-16K
    6. 2150
    Prev
    Next
    INDEX
    Explanations

    words that relate to collaboration or partnerships in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ་་
    -0.85
     Theſe
    -0.83
     ―――――
    -0.81
     Beſ
    -0.74
     verſ
    -0.74
     itſelf
    -0.72
     ſind
    -0.70
     iconFacebook
    -0.69
     iſt
    -0.68
    مراجع
    -0.67
    POSITIVE LOGITS
     Ne
    0.87
    Lähteet
    0.86
    Ne
    0.84
    Ge
    0.83
    Su
    0.83
     Ma
    0.82
    Ma
    0.82
     Su
    0.82
     Ge
    0.81
     re
    0.81
    Activations Density 0.283%

    No Known Activations