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. 19-GEMMASCOPE-RES-16K
    6. 3927
    Prev
    Next
    INDEX
    Explanations

    concepts related to methodological approaches and data analysis techniques in scientific research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -1.00
     تضيفلها
    -0.63
    ApiModelProperty
    -0.62
     AssemblyProduct
    -0.60
     kaarangay
    -0.60
    σθαι
    -0.59
    IndentedString
    -0.57
    ">—
    -0.56
    IntoConstraints
    -0.56
     himo
    -0.55
    POSITIVE LOGITS
     method
    2.74
     methods
    2.65
    method
    2.37
    methods
    2.27
     Method
    2.25
     techniques
    2.25
     technique
    2.24
     méthode
    2.16
    Method
    2.15
     methodology
    2.14
    Activations Density 1.711%

    No Known Activations