© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 5919
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives and their modifiers that describe quality or effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cabe
    -0.53
    ษัท
    -0.47
     voulu
    -0.46
     brasileiros
    -0.46
    وان
    -0.46
     objet
    -0.45
     fallu
    -0.45
    <eos>
    -0.43
    add
    -0.43
     emerges
    -0.43
    POSITIVE LOGITS
     disambiguazione
    0.94
    jstor
    0.75
    onedDateTime
    0.74
    Portale
    0.66
    Externé
    0.66
    CppCodeGen
    0.66
     lenker
    0.65
     كومونز
    0.64
    mappedBy
    0.64
    AddTagHelper
    0.64
    Activations Density 0.625%

    No Known Activations