© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 78580
    Prev
    Next
    INDEX
    Explanations

    topics related to healthcare, scientific research, and significant public interest stories

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

    financial and event reporting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mantequilla
    -0.32
     öne
    -0.30
     affaire
    -0.26
     hooked
    -0.26
     selección
    -0.24
    hodné
    -0.23
     máscaras
    -0.23
     pareja
    -0.23
     sní
    -0.22
     mentira
    -0.22
    POSITIVE LOGITS
     betweenstory
    1.03
     queſta
    0.85
     onCreateView
    0.81
    makeText
    0.71
    enterOuterAlt
    0.69
     ainfi
    0.68
     linkovi
    0.68
    intios
    0.68
    arraycopy
    0.66
     AssemblyVersion
    0.65
    Activations Density 0.236%

    No Known Activations