© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 9844
    Prev
    Next
    INDEX
    Explanations

    references to 'form' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -1.21
    "])
    -0.91
    Rüyada
    -0.90
    rungsseite
    -0.84
    )");
    -0.82
    "]);
    -0.81
    "):
    -0.81
    lihood
    -0.80
     Keegan
    -0.78
     nî
    -0.78
    POSITIVE LOGITS
     form
    3.15
     Form
    2.94
     FORM
    2.85
    form
    2.80
     forms
    2.78
    Form
    2.72
     Forms
    2.71
     FORMS
    2.52
    forms
    2.47
    FORM
    2.40
    Activations Density 0.076%

    No Known Activations