© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 2326
    Prev
    Next
    INDEX
    Explanations

    elements related to mathematical and statistical concepts, especially those involving graphs and properties of distributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tonode
    -0.82
    fjspx
    -0.76
    ----</
    -0.65
     AssemblyCulture
    -0.63
     INTERESAR
    -0.62
     שוליים
    -0.62
    URLException
    -0.61
    GOTREF
    -0.60
    webElementXpaths
    -0.59
    RegressionTest
    -0.59
    POSITIVE LOGITS
     much
    0.34
    罩
    0.32
     vibr
    0.30
     comp
    0.29
     mel
    0.28
    就
    0.27
    Switcher
    0.27
     Mel
    0.26
     sat
    0.26
    évaluateur
    0.26
    Activations Density 3.553%

    No Known Activations