© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 4226
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and syntax references

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

    Eclipse-related modeling and XML structures

    np_acts-logits-general · gemini-2.0-flash

    UML object-oriented modeling

    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
    Климат
    -0.59
    DebuggerNonUser
    -0.53
    ArgsConstructor
    -0.53
    LabelTagHelper
    -0.53
    !*\
    -0.53
    UniformLocation
    -0.51
     Proben
    -0.50
    ApiException
    -0.49
    twimg
    -0.49
     biennial
    -0.48
    POSITIVE LOGITS
    ecore
    0.68
     stereotypes
    0.61
     Stere
    0.61
     modeling
    0.60
     EMF
    0.59
     modelling
    0.59
     containment
    0.57
     stereotype
    0.56
    Stere
    0.56
     UML
    0.55
    Activations Density 0.163%

    No Known Activations