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. 24-GEMMASCOPE-RES-16K
    6. 4537
    Prev
    Next
    INDEX
    Explanations

    symbols, special characters, and technical notations in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text formatting or markup

    np_acts-logits-general · gemini-2.0-flash

    brackets and special characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsContent
    -1.04
    SourceChecksum
    -1.03
    Hentet
    -1.00
     initComponents
    -0.96
    AddTagHelper
    -0.96
     nahilalakip
    -0.89
    AndEndTag
    -0.88
    LookAnd
    -0.88
     transfieras
    -0.86
    AccessorTable
    -0.86
    POSITIVE LOGITS
    																													
    0.78
    																														
    0.69
    saurus
    0.66
    ️
    0.65
    																							
    0.65
    etera
    0.65
    OrEmpty
    0.64
    																								
    0.62
     itſelf
    0.59
    âtre
    0.58
    Activations Density 2.453%

    No Known Activations