© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 13783
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistical information

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

    Sentences ending with a period

    np_acts-logits-general · gemini-2.0-flash

    survivors and services

    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
    principalColumn
    -0.64
    ValueStyle
    -0.61
    pshire
    -0.60
    我才
    -0.56
    unehmen
    -0.55
    anmoins
    -0.55
    WebElementEntity
    -0.54
     CreateTagHelper
    -0.51
    éndolo
    -0.51
     AssemblyCompany
    -0.51
    POSITIVE LOGITS
     Survivors
    1.05
     Survi
    1.03
    Survivors
    1.00
    Surviving
    0.99
     survivors
    0.91
     Services
    0.89
     surviving
    0.88
    Services
    0.88
    survi
    0.85
    Survi
    0.85
    Activations Density 0.020%

    No Known Activations