© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 7649
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to medical or biological conditions and their classifications

    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
    y
    -1.91
    o
    -1.70
    i
    -1.46
    e
    -1.41
    a
    -1.41
    t
    -1.40
    ه
    -1.37
    er
    -1.24
    en
    -1.21
    s
    -1.20
    POSITIVE LOGITS
     AssemblyCulture
    1.29
    Manbalar
    1.28
     Efq
    1.20
     Rasp
    1.18
     prosegu
    1.17
     COB
    1.17
     MEG
    1.15
    rijf
    1.13
    thest
    1.13
    Viitteet
    1.12
    Activations Density 6.426%

    No Known Activations