© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 16255
    Prev
    Next
    INDEX
    Explanations

    contact information and inquiries related to a program or organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atrième
    -0.50
    bietern
    -0.46
     propOrder
    -0.45
    enumi
    -0.44
    就
    -0.43
     smell
    -0.42
    MessageOf
    -0.41
     Fourth
    -0.41
    \}\\
    -0.41
    ruary
    -0.41
    POSITIVE LOGITS
     contact
    0.79
    contact
    0.74
     emailing
    0.71
     Email
    0.71
     contacts
    0.69
     email
    0.68
    Email
    0.67
     Contacts
    0.67
    WithIOException
    0.67
     contacting
    0.66
    Activations Density 0.163%

    No Known Activations