© 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. 8-GEMMASCOPE-RES-16K
    6. 1879
    Prev
    Next
    INDEX
    Explanations

    expressions of support and encouragement for pursuing goals and dreams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lapsing
    -0.50
     CreateTagHelper
    -0.49
    уго
    -0.48
    umably
    -0.48
    \{\\
    -0.47
    Complement
    -0.47
    kib
    -0.46
    čil
    -0.46
    ūra
    -0.46
    Público
    -0.44
    POSITIVE LOGITS
     propOrder
    0.96
     motivational
    0.89
     mentorship
    0.77
     Empowerment
    0.76
     inspirational
    0.75
     empowerment
    0.75
     Inspirational
    0.75
     Entrepreneur
    0.73
     career
    0.71
     entrepreneurial
    0.70
    Activations Density 0.255%

    No Known Activations