© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4265
    Prev
    Next
    INDEX
    Explanations

    technical terms related to validation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Inspection, validation, or verification

    np_acts-logits-general · gemini-2.0-flash

    inspection and validation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PreferredItem
    -0.48
    艋
    -0.45
    GeneratedMessage
    -0.44
     endwhile
    -0.43
    
    -0.43
    ngrx
    -0.40
    abestanden
    -0.39
     TextAlign
    -0.38
    ChildScrollView
    -0.38
    \{\\
    -0.38
    POSITIVE LOGITS
     inspection
    1.20
     inspections
    1.16
     checks
    1.14
     verification
    1.13
     checking
    1.05
     검
    1.04
     vérification
    1.03
     verifying
    1.03
     inspectors
    1.02
     inspecting
    1.02
    Activations Density 0.651%

    No Known Activations