© 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-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 7065
    Prev
    Next
    INDEX
    Explanations

    mathematical conditions and properties related to statistical estimators in advanced models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     szám
    -0.38
    KEYCODE
    -0.38
    iredo
    -0.36
     Aufs
    -0.36
     Wikiseite
    -0.35
    Ferdin
    -0.35
    CloseOperation
    -0.34
    RunWith
    -0.33
     darbu
    -0.33
    insegna
    -0.33
    POSITIVE LOGITS
     requirements
    0.94
     requirement
    0.94
     constraints
    0.93
     conditions
    0.86
     assumptions
    0.84
     constraint
    0.84
     condition
    0.84
     imposed
    0.81
     Requirement
    0.81
     restrictions
    0.80
    Activations Density 2.567%

    No Known Activations