© 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. 4145
    Prev
    Next
    INDEX
    Explanations

    specific data and terms related to legal and medical documentation

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

    Tokens preceding suffixes like "-ant", "-ance", "-ans"

    np_acts-logits-general · gemini-2.0-flash

    Christianised, resonant, dominant, sections, antigen

    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
    StateException
    -0.51
     []:
    -0.48
     Sodom
    -0.47
    __);
    -0.46
     Clyde
    -0.46
    InvalidProtocol
    -0.46
    Lähteet
    -0.46
    omene
    -0.46
     AssemblyCompany
    -0.45
    plona
    -0.45
    POSITIVE LOGITS
     An
    1.82
    An
    1.77
     AN
    1.68
    AN
    1.59
    an
    1.36
    ans
    1.32
    ann
    1.24
    ANS
    1.22
    ANT
    1.16
     ann
    1.13
    Activations Density 0.916%

    No Known Activations