© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 13816
    Prev
    Next
    INDEX
    Explanations

    mentions of processes or concepts related to development and effectiveness

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

    successful, promising, satisfactory, useful

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    förmig
    -0.29
    petto
    -0.29
    eseorang
    -0.28
    ńczy
    -0.27
    GeneratedValue
    -0.27
     Parce
    -0.27
     Forgiveness
    -0.26
    Permission
    -0.26
    Microkernel
    -0.26
    orthand
    -0.25
    POSITIVE LOGITS
     inadequate
    1.23
     unsatisfactory
    1.20
     disappointing
    1.19
     insufficient
    1.16
     špat
    1.11
     inadequ
    1.10
     disappoint
    1.09
     failed
    1.09
     inefficient
    1.09
     ineffective
    1.08
    Activations Density 0.878%

    No Known Activations