Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 14796
    Prev
    Next
    INDEX
    Explanations

    instances of the word "standing."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    })));
    -0.76
    OuterClass
    -0.61
     /\.
    -0.60
    améli
    -0.59
     NgModule
    -0.57
    OrBuilder
    -0.57
    OutputPath
    -0.57
    NamedQueries
    -0.57
    дневно
    -0.55
     selatan
    -0.55
    POSITIVE LOGITS
     standing
    3.39
     Standing
    3.18
    Standing
    3.00
    standing
    2.72
    STANDING
    1.96
     debout
    1.68
     sitting
    1.50
     seated
    1.33
     стоя
    1.32
     Sitting
    1.30
    Activations Density 0.069%

    No Known Activations