© 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-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 11557
    Prev
    Next
    INDEX
    Explanations

    expressions or phrases related to evaluations and assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RTEX
    -0.76
     resourceCulture
    -0.75
     estekak
    -0.73
     صوتيه
    -0.72
    errHandler
    -0.70
    protoc
    -0.69
     autorytatywna
    -0.69
     transférez
    -0.69
     nakalista
    -0.68
    StoryboardSegue
    -0.67
    POSITIVE LOGITS
     Plus
    1.40
    Plus
    1.39
     plus
    1.19
    Moreover
    1.15
    plus
    1.14
     Moreover
    1.09
     PLUS
    1.06
    更何况
    1.01
    何况
    1.00
     Außerdem
    0.97
    Activations Density 0.584%

    No Known Activations