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. 10-GEMMASCOPE-RES-16K
    6. 2988
    Prev
    Next
    INDEX
    Explanations

    sentence-ending punctuation, indicating the conclusion of thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FetchType
    -0.84
    odotus
    -0.75
    конец
    -0.75
    ugeot
    -0.74
     vixion
    -0.72
    arangay
    -0.71
    NUMX
    -0.69
    LEncoder
    -0.68
    ésult
    -0.68
     
    -0.67
    POSITIVE LOGITS
    .
    1.15
    ))).
    1.09
    <eos>
    1.08
    }$.
    1.07
    $.
    1.05
    ).
    1.03
    }.
    1.03
    ])).
    1.03
    ↵↵
    1.03
    ))$.
    1.03
    Activations Density 2.565%

    No Known Activations