© 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. 1-GEMMASCOPE-RES-16K
    6. 13109
    Prev
    Next
    INDEX
    Explanations

    verbs indicating a start or progression of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    实的
    -0.57
    ()];
    -0.57
    )}_
    -0.56
     makl
    -0.55
    ()]);
    -0.54
     marvellous
    -0.54
    																						
    -0.54
     Ambiental
    -0.52
     Geoffrey
    -0.52
     mercen
    -0.52
    POSITIVE LOGITS
     began
    1.86
    began
    1.60
     Began
    1.31
     became
    1.05
     comenzó
    1.04
     beginning
    1.02
    beginning
    0.98
     comenzaron
    0.97
     grew
    0.96
     BEGINNING
    0.93
    Activations Density 0.110%

    No Known Activations