© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 9102
    Prev
    Next
    INDEX
    Explanations

    anatomical terms related to surgical procedures and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TLS
    -0.45
    tonsoft
    -0.43
    
    -0.42
     LET
    -0.41
     loginUser
    -0.41
    EditForm
    -0.40
     Let
    -0.40
    acty
    -0.40
    edos
    -0.40
    iterraneo
    -0.40
    POSITIVE LOGITS
    IntoConstraints
    0.97
    sidemargin
    0.81
    حوالہ
    0.80
     '\\;'
    0.75
     tartalomajánló
    0.72
     ExecuteAsync
    0.72
    adaptiveStyles
    0.72
     autorytatywna
    0.71
     camicia
    0.70
    MethodManager
    0.70
    Activations Density 0.777%

    No Known Activations