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. 21-GEMMASCOPE-RES-16K
    6. 14960
    Prev
    Next
    INDEX
    Explanations

    references to Microsoft technologies and products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ref
    -0.38
     preju
    -0.38
     perkara
    -0.38
    Ещё
    -0.38
     menga
    -0.37
    about
    -0.37
    phemy
    -0.36
    diksi
    -0.36
     class
    -0.35
    ubre
    -0.35
    POSITIVE LOGITS
     betweenstory
    1.19
    AspNetCore
    0.80
    ContentAsync
    0.79
     صوتيه
    0.79
     utafitiHapana
    0.75
    /**
    0.74
     Италијани
    0.69
     Ronan
    0.68
    UnknownFields
    0.66
    estacks
    0.66
    Activations Density 0.048%

    No Known Activations