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. 11-GEMMASCOPE-RES-16K
    6. 6849
    Prev
    Next
    INDEX
    Explanations

    references to programming syntax and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     big
    -0.54
    -
    -0.48
     BIG
    -0.48
    BIG
    -0.48
    big
    -0.46
    mfenced
    -0.44
     opie
    -0.42
    Big
    -0.42
    ਭ
    -0.41
    chenkt
    -0.41
    POSITIVE LOGITS
    Geplaatst
    1.04
    HostException
    1.04
    endphp
    1.03
    toMatchSnapshot
    1.01
     esternos
    0.93
     صوتيه
    0.93
     GeoNames
    0.85
    Datuak
    0.85
    bcryptjs
    0.85
    NameInMap
    0.82
    Activations Density 0.524%

    No Known Activations