Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 15578
    Prev
    Next
    INDEX
    Explanations

    financial figures and statistical data points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     NgModule
    -0.71
    izop
    -0.70
    StoryboardSegue
    -0.69
    isiä
    -0.68
    CodedInputStream
    -0.68
    uldron
    -0.65
     Ayres
    -0.63
     Piv
    -0.62
    krivning
    -0.60
    \{\\
    -0.60
    POSITIVE LOGITS
     defaultdict
    0.80
     EDD
    0.79
     PPS
    0.77
    😍😍
    0.77
     Manne
    0.77
    Datuak
    0.76
     YY
    0.76
     Dott
    0.76
    mms
    0.76
     Hatt
    0.75
    Activations Density 0.524%

    No Known Activations