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. 4-GEMMASCOPE-RES-16K
    6. 16023
    Prev
    Next
    INDEX
    Explanations

    terms related to pharmaceutical and clinical research content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    |')
    -0.60
     CreateTagHelper
    -0.60
    voie
    -0.54
     Look
    -0.49
    VarChar
    -0.48
    gli
    -0.48
    理由は
    -0.48
     Big
    -0.48
    valu
    -0.47
    Contours
    -0.47
    POSITIVE LOGITS
     صوتيه
    0.75
     product
    0.75
    FXML
    0.71
     produto
    0.69
    /**
    0.68
     المعيارى
    0.68
     })}
    0.67
    msgTypes
    0.65
     prodotto
    0.65
    PYX
    0.64
    Activations Density 0.892%

    No Known Activations