© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 28035
    Prev
    Next
    INDEX
    Explanations

    technical components and terminology related to mechanical and electrical systems

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

    device components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.96
     CreateTagHelper
    -0.93
    ValueStyle
    -0.89
     صوتيه
    -0.88
    الإنجليزية
    -0.86
     nakalista
    -0.84
    URLException
    -0.84
     للمعارف
    -0.80
    SequentialGroup
    -0.80
     يتيمه
    -0.79
    POSITIVE LOGITS
    </b>
    0.27
     kellett
    0.26
     inilah
    0.26
     dernières
    0.25
     hovor
    0.25
     sammen
    0.24
    わけです
    0.24
     cuidadosamente
    0.24
     comunión
    0.23
     usually
    0.23
    Activations Density 0.126%

    No Known Activations