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. 15927
    Prev
    Next
    INDEX
    Explanations

    instances of speech or communication within the text

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

    Followed by a verb indicating speech

    np_acts-logits-general · gemini-2.0-flash

    speaking to audiences

    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
     asti
    -0.54
     Mahomet
    -0.49
    жнему
    -0.48
     tfsi
    -0.48
     yzf
    -0.47
     recommandons
    -0.47
    adto
    -0.46
    quê
    -0.45
    BRC
    -0.45
     RTP
    -0.45
    POSITIVE LOGITS
     snippetHide
    0.77
     utafitiHapana
    0.73
     audiences
    0.71
    SBATCH
    0.70
     audience
    0.70
    zzleHttp
    0.69
    Slf
    0.68
    AttributeSet
    0.65
    دانشنامهٔ
    0.64
    httphttps
    0.64
    Activations Density 0.166%

    No Known Activations