© 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. 6507
    Prev
    Next
    INDEX
    Explanations

    terms and references related to symmetry in various contexts

    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
     فريبيس
    -0.64
    )];
    
    -0.56
     SEDS
    -0.56
    RTEX
    -0.55
     tartalomajánló
    -0.55
    ąb
    -0.54
     together
    -0.54
     contextLoads
    -0.53
     ใหม่
    -0.53
     télévisée
    -0.53
    POSITIVE LOGITS
    __*/
    0.70
    AxisAlignment
    0.68
    ó
    0.60
    symmetric
    0.59
    IMPORTED
    0.55
     symmetric
    0.54
     pinulongan
    0.54
    GroupLayout
    0.53
     onResponse
    0.52
    sian
    0.51
    Activations Density 2.759%

    No Known Activations