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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 2883
    Prev
    Next
    INDEX
    Explanations

    references to anonymity and the withholding of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DIPSETTING
    -0.66
     nakalista
    -0.56
    קישורים
    -0.55
    Denomin
    -0.54
    ogues
    -0.54
    ✭✭
    -0.54
    juvant
    -0.53
     Anhäng
    -0.53
    таратура
    -0.52
     paroisse
    -0.51
    POSITIVE LOGITS
    BeginContext
    0.65
    Geplaatst
    0.60
    GEBURTSDATUM
    0.60
    PRNewswire
    0.57
    SuppressLint
    0.54
    ErrorException
    0.53
    تقاوى
    0.51
     kotlinx
    0.50
     withheld
    0.47
    dotenv
    0.46
    Activations Density 0.174%

    No Known Activations