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. 9-GEMMASCOPE-RES-16K
    6. 1381
    Prev
    Next
    INDEX
    Explanations

    financial metrics and indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gains
    -0.55
     gain
    -0.51
    xhttp
    -0.49
     καν
    -0.49
     remember
    -0.47
    IVEREF
    -0.47
     even
    -0.47
    UTELY
    -0.47
     surely
    -0.47
     get
    -0.46
    POSITIVE LOGITS
     postIndex
    0.72
     confocal
    0.72
    GEBURTSDATUM
    0.72
     Majefty
    0.71
     Reverso
    0.71
     BorderSide
    0.71
     japonaise
    0.71
     ainfi
    0.69
     nephe
    0.68
     grecque
    0.68
    Activations Density 0.113%

    No Known Activations