© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 3215
    Prev
    Next
    INDEX
    Explanations

    phrases related to processes or methods of analysis and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WireFormatLite
    -0.86
    fromnode
    -0.80
     ProtoMessage
    -0.71
    MessageOf
    -0.70
     esternos
    -0.70
    MessageTagHelper
    -0.68
    PropertyChanging
    -0.65
    何より
    -0.61
    ]")]
    -0.59
    SerializedSize
    -0.59
    POSITIVE LOGITS
     to
    0.76
     ensuring
    0.62
     Afin
    0.61
     чтобы
    0.59
     achieve
    0.58
     trying
    0.57
    Afin
    0.56
     ensure
    0.55
     achieving
    0.55
     supaya
    0.55
    Activations Density 0.069%

    No Known Activations