© 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-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 13098
    Prev
    Next
    INDEX
    Explanations

    contact information and organizational details

    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
    twimg
    -0.52
     vache
    -0.46
     dag
    -0.45
     Verpflichtung
    -0.43
     MyApp
    -0.42
     beginnetje
    -0.41
    tvguidetime
    -0.41
     Gustaf
    -0.41
     here
    -0.40
    BorderLayout
    -0.40
    POSITIVE LOGITS
     فريبيس
    0.71
     disambiguazione
    0.69
    enterOuterAlt
    0.67
    BufferException
    0.66
     ExecuteAsync
    0.66
    --*/
    0.66
    RUnlock
    0.64
    TagHelper
    0.63
    rungsseite
    0.62
    ksesta
    0.61
    Activations Density 0.145%

    No Known Activations