© 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. 25-GEMMASCOPE-RES-16K
    6. 8984
    Prev
    Next
    INDEX
    Explanations

    specific references to funding sources and institutional acknowledgments in research studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.65
    +#+
    -0.63
    typeparam
    -0.60
    lccn
    -0.60
    AutoScale
    -0.59
    SizeF
    -0.54
     Superhost
    -0.52
    willReturn
    -0.52
    CppMethod
    -0.52
    Hentet
    -0.51
    POSITIVE LOGITS
     translational
    0.68
     investigators
    0.68
    tagHelperRunner
    0.64
     investigator
    0.62
     Trans
    0.56
     Investigator
    0.53
     NIE
    0.53
    Trans
    0.53
     Investigators
    0.52
    TRANSL
    0.52
    Activations Density 0.559%

    No Known Activations