Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 0-GEMMASCOPE-RES-16K
    6. 7636
    Prev
    Next
    INDEX
    Explanations

    terms related to the act of providing or delivering services and solutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EDEFAULT
    -0.85
    Kjelder
    -0.84
     MessageBoxIcon
    -0.82
     متعلقه
    -0.81
    enumii
    -0.81
     nahilalakip
    -0.80
     contextLoads
    -0.79
     insuffisamment
    -0.77
     actionTypes
    -0.77
     karat
    -0.77
    POSITIVE LOGITS
     providing
    2.40
     provide
    2.31
     provides
    2.13
     Providing
    2.11
    Providing
    2.10
     provided
    2.08
    provide
    2.08
    providing
    2.08
     Provide
    2.01
    Provide
    2.00
    Activations Density 0.158%

    No Known Activations