© 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-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 7862
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to concerns or worries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.84
    ReusableCell
    -0.57
    providedIn
    -0.57
    TabIndex
    -0.50
     BoxDecoration
    -0.49
    StoryboardSegue
    -0.49
    たまた
    -0.48
    Xaml
    -0.48
    libft
    -0.47
    ViewFeatures
    -0.47
    POSITIVE LOGITS
     whether
    0.46
     lest
    0.44
     ciudadano
    0.43
     främ
    0.39
     raised
    0.38
    忡
    0.38
    RenderAtEndOf
    0.37
    whether
    0.37
     expressed
    0.35
     tráfico
    0.35
    Activations Density 0.135%

    No Known Activations