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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 10505
    Prev
    Next
    INDEX
    Explanations

    structured data formats and declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.53
    uppercase
    -0.51
    dsk
    -0.50
    glGet
    -0.48
    tele
    -0.47
     Kni
    -0.47
    Svc
    -0.47
    holi
    -0.47
    preter
    -0.47
    rinfo
    -0.46
    POSITIVE LOGITS
     ditto
    1.07
    IntoConstraints
    0.84
    ditto
    0.75
     TAMBÉM
    0.72
     EconPapers
    0.69
     altrett
    0.67
    StructEnd
    0.66
     nakalista
    0.65
     тоже
    0.65
     correspondingly
    0.64
    Activations Density 2.070%

    No Known Activations