© 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. 9-GEMMASCOPE-RES-131K
    6. 97121
    Prev
    Next
    INDEX
    Explanations

    references to components and functions related to Amazon Kinesis and its associated libraries

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

    Amazon Kinesis

    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
     initComponents
    -0.49
    tonode
    -0.39
     snippetHide
    -0.38
    Referències
    -0.38
    Collegamenti
    -0.38
    enschappelijke
    -0.37
    évaluateur
    -0.36
    êques
    -0.35
     QtWidgets
    -0.35
    Przypisy
    -0.35
    POSITIVE LOGITS
     ويكيميديا
    0.95
    iverr
    0.81
     Darfur
    0.71
    ombic
    0.67
    Tikang
    0.65
    IBar
    0.63
    popularity
    0.59
    ForValue
    0.53
     Fordham
    0.52
     Picchu
    0.51
    Activations Density 0.006%

    No Known Activations