© 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. 9-GEMMASCOPE-RES-16K
    11. 15997
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to liability and court decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    geslacht
    -0.52
     consultato
    -0.49
     tranquila
    -0.48
     Investi
    -0.48
     Portuguese
    -0.48
     pican
    -0.47
     Calm
    -0.47
    مل
    -0.46
    HasColumnName
    -0.45
     calmness
    -0.45
    POSITIVE LOGITS
    kheim
    0.59
    Демографія
    0.58
     mechanism
    0.56
    mechanism
    0.56
    WriteTagHelper
    0.56
     برانيه
    0.55
     justiça
    0.55
    ēju
    0.54
    protoimpl
    0.53
    ostom
    0.53
    Activations Density 0.902%

    No Known Activations