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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 11169
    Prev
    Next
    INDEX
    Explanations

    references to the Māori king Pōmare and associated historical figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.73
     myſelf
    -0.72
    NameInMap
    -0.70
    HttpPut
    -0.70
     Nó
    -0.69
    HttpPost
    -0.68
     OFDb
    -0.66
     ſtill
    -0.66
    Predecesor
    -0.65
     ――――
    -0.65
    POSITIVE LOGITS
    }
    0.59
    "
    0.57
    <em>
    0.57
    ReusableCell
    0.56
    <eos>
    0.49
    lindungan
    0.48
    )
    0.48
    Otherwise
    0.47
    Hochspringen
    0.47
     otherwise
    0.47
    Activations Density 0.027%

    No Known Activations