© 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. 16196
    Prev
    Next
    INDEX
    Explanations

    references to a central location or focal point

    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
     bestehen
    -0.57
     '
    -0.56
     Rosenberg
    -0.55
    PerformLayout
    -0.55
    سد
    -0.54
    todo
    -0.53
     seno
    -0.52
    <u>
    -0.52
    "],
    
    -0.52
     opdracht
    -0.51
    POSITIVE LOGITS
     Hub
    1.36
    hub
    1.30
     hub
    1.29
    Hub
    1.27
     HUB
    1.11
     hubs
    1.04
    HUB
    0.94
     Braw
    0.81
     ddelweddau
    0.81
     Ctrl
    0.79
    Activations Density 0.078%

    No Known Activations