Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 11052
    Prev
    Next
    INDEX
    Explanations

    chemical structures and molecular properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.63
    Personensuche
    -0.60
    WriteBarrier
    -0.55
     חיצוניים
    -0.55
     CURLOPT
    -0.53
     viewWillAppear
    -0.50
    entgen
    -0.50
    InputTagHelper
    -0.50
     مشين
    -0.48
    : 
    -0.48
    POSITIVE LOGITS
    opsida
    0.61
    nsis
    0.60
     MonoBehaviour
    0.58
    MessageTagHelper
    0.57
    wts
    0.53
    setViewportView
    0.52
     istället
    0.52
    laszt
    0.51
     Asp
    0.51
     ujarnya
    0.50
    Activations Density 0.465%

    No Known Activations