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. 16-GEMMASCOPE-RES-16K
    6. 4307
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication and interpersonal interactions

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

    Follows coordinating conjunctions

    np_acts-logits-general · gemini-2.0-flash

    images and

    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
     berbicara
    -0.57
    MessageInfo
    -0.56
     déclarations
    -0.54
     comentarios
    -0.53
     falar
    -0.52
     keterangan
    -0.52
     comment
    -0.52
     commento
    -0.50
     civilian
    -0.50
     hablan
    -0.49
    POSITIVE LOGITS
     utafitiHapana
    0.79
     pictures
    0.72
     visuals
    0.70
     purpoſe
    0.69
     myſelf
    0.69
     pleaſure
    0.67
     images
    0.65
    ภาพ
    0.65
     themſelves
    0.64
     photos
    0.63
    Activations Density 0.616%

    No Known Activations