© 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. 4167
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming concepts and object-oriented principles

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

    Followed by the word "message"

    np_acts-logits-general · gemini-2.0-flash

    messages and related events

    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
    WriteLiteral
    -0.57
     EnglishChoose
    -0.54
    LookAnd
    -0.53
     curtains
    -0.50
     papers
    -0.48
     park
    -0.48
    ynb
    -0.48
     CURIAM
    -0.47
    CppMethod
    -0.47
    knex
    -0.47
    POSITIVE LOGITS
     message
    3.56
    message
    3.26
     Message
    2.95
    Message
    2.81
     MESSAGE
    2.62
     messages
    2.57
    MESSAGE
    2.36
     mensaje
    2.29
     Messages
    2.12
     mensagem
    2.10
    Activations Density 0.140%

    No Known Activations