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. 16-GEMMASCOPE-RES-16K
    6. 15890
    Prev
    Next
    INDEX
    Explanations

    punctuation marks that indicate the end of a sentence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Sentences immediately following periods

    np_acts-logits-general · gemini-2.0-flash

    punctuation and following words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -0.86
    )".
    -0.77
    ']").
    -0.77
    ]").
    -0.75
    <eos>
    -0.75
    ).”
    -0.72
    ViewFeatures
    -0.71
    )”.
    -0.70
    '}),
    -0.68
    InvalidProtocol
    -0.68
    POSITIVE LOGITS
    Anyway
    0.63
     Anyway
    0.61
     незавершена
    0.60
     Anyways
    0.53
    Anyways
    0.52
    Recently
    0.51
    さて
    0.51
     quoque
    0.50
     fasc
    0.49
     típica
    0.48
    Activations Density 0.646%

    No Known Activations