© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 10798
    Prev
    Next
    INDEX
    Explanations

    personal reflections and expressions of emotional states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sklici
    -0.47
     tetapi
    -0.44
     conclusão
    -0.43
     hombros
    -0.43
     cauza
    -0.42
     courants
    -0.42
     leçons
    -0.40
     relazione
    -0.40
     sementara
    -0.40
     sélectionnez
    -0.40
    POSITIVE LOGITS
    ########.
    1.21
     تضيفلها
    0.92
    StoryboardSegue
    0.88
    makeConstraints
    0.85
     /\.
    0.84
     CURIAM
    0.80
    migrationBuilder
    0.77
     tartalomajánló
    0.74
     defaultstate
    0.71
    esgue
    0.71
    Activations Density 5.179%

    No Known Activations