© 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. 14-GEMMASCOPE-RES-16K
    6. 12770
    Prev
    Next
    INDEX
    Explanations

    numerical values and expressions related to mathematical operations and factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CardType
    -0.66
    CloseOperation
    -0.62
     Gunter
    -0.60
    aguchi
    -0.59
     ddelweddau
    -0.59
     CreateTagHelper
    -0.58
     InputDecoration
    -0.58
     Eno
    -0.54
    Tol
    -0.53
    vician
    -0.53
    POSITIVE LOGITS
     oprot
    0.88
     initComponents
    0.82
    Diwedd
    0.68
     cdti
    0.66
     ISNI
    0.65
     propOrder
    0.65
    cipais
    0.64
     useHistory
    0.61
    DebuggerStep
    0.61
    Fischer
    0.61
    Activations Density 0.922%

    No Known Activations