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. 10-GEMMASCOPE-RES-16K
    6. 10712
    Prev
    Next
    INDEX
    Explanations

    programming language constructs and definitions, particularly related to constants, data types, and static variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MLLoader
    -0.68
    reszcie
    -0.63
    iprot
    -0.57
    createServer
    -0.55
    CodedInputStream
    -0.55
    __":
    
    -0.54
    élien
    -0.53
    tonsoft
    -0.53
    EMPL
    -0.52
     ogóle
    -0.52
    POSITIVE LOGITS
    IBOutlet
    0.75
    Constants
    0.64
    RetentionPolicy
    0.60
    StandardCharsets
    0.60
    constants
    0.57
     StyleSheet
    0.57
    DllImport
    0.56
     constants
    0.55
    hyrchwyd
    0.54
    Rhestr
    0.54
    Activations Density 0.171%

    No Known Activations