© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 11379
    Prev
    Next
    INDEX
    Explanations

    instances of division or allocation of resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Connecting
    -0.41
     layak
    -0.41
     Dicapai
    -0.38
    zesz
    -0.38
     obligado
    -0.38
    es
    -0.38
     liitty
    -0.37
    n
    -0.36
    ester
    -0.36
     Elvira
    -0.36
    POSITIVE LOGITS
    IsContent
    0.89
    aarrggbb
    0.80
     dividir
    0.79
    +#+#
    0.78
     splitting
    0.78
     evenly
    0.76
     partag
    0.76
     Divided
    0.75
     partage
    0.74
     sharing
    0.74
    Activations Density 0.391%

    No Known Activations