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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 3918
    Prev
    Next
    INDEX
    Explanations

    words related to chemical compounds and therapies in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntentFilter
    -0.62
    行政区划
    -0.61
     réguli
    -0.59
    cionario
    -0.58
    principalTable
    -0.58
    DIPSETTING
    -0.55
    exels
    -0.55
     pouvoirs
    -0.53
     sauvages
    -0.53
     dirait
    -0.53
    POSITIVE LOGITS
     che
    0.71
    Che
    0.70
     Che
    0.70
    che
    0.63
     chi
    0.63
     onCreateView
    0.60
     CHE
    0.59
     itſelf
    0.57
    chim
    0.56
     Theſe
    0.56
    Activations Density 2.127%

    No Known Activations