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. 17-GEMMASCOPE-RES-16K
    6. 10762
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or probability

    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
    D
    -0.57
    R
    -0.56
    A
    -0.54
    M
    -0.50
    on
    -0.47
    -
    -0.47
    ck
    -0.47
    CK
    -0.46
    K
    -0.46
    C
    -0.46
    POSITIVE LOGITS
    GEBURTSDATUM
    0.89
    цездатний
    0.85
    ThemeProvider
    0.84
    >\<^
    0.83
    bably
    0.83
    Personensuche
    0.83
    ########.
    0.80
    klü
    0.80
    tonsoft
    0.78
    DockStyle
    0.78
    Activations Density 0.131%

    No Known Activations