© 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. 11-GEMMASCOPE-RES-16K
    11. 2103
    Prev
    Next
    INDEX
    Explanations

    features related to materials and their properties, especially in textiles and absorbent articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HomeAsUpEnabled
    -0.91
     Efq
    -0.86
    SourceChecksum
    -0.83
     متعلقه
    -0.83
    AndroidJUnit
    -0.83
     Theſe
    -0.81
    GOTREF
    -0.81
     defaultstate
    -0.79
    ModelAdmin
    -0.76
    TagMode
    -0.76
    POSITIVE LOGITS
     layer
    0.62
     layers
    0.59
    层
    0.56
     material
    0.54
    層
    0.54
    layer
    0.53
    layers
    0.53
     inside
    0.51
     liner
    0.49
     lapisan
    0.49
    Activations Density 0.331%

    No Known Activations