© 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. 2-GEMMASCOPE-RES-16K
    6. 8067
    Prev
    Next
    INDEX
    Explanations

    expressions related to acceptance and widely recognized standards or practices

    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
    CodeAnalysis
    -0.64
    èvent
    -0.63
     Steff
    -0.63
    hoga
    -0.60
    URLException
    -0.59
    IDL
    -0.57
    onView
    -0.57
     Quay
    -0.57
     tattoos
    -0.55
     CGA
    -0.55
    POSITIVE LOGITS
     accepted
    1.76
     respected
    1.55
     Accepted
    1.55
    accepted
    1.49
     trusted
    1.40
     recognised
    1.39
    respected
    1.35
    Accepted
    1.32
     recognized
    1.27
     approved
    1.19
    Activations Density 0.188%

    No Known Activations