© 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. 22-GEMMASCOPE-RES-16K
    6. 16295
    Prev
    Next
    INDEX
    Explanations

    constructs related to logical reasoning and problem-solving

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

    exclusion or alternatives

    np_acts-logits-general · gemini-2.0-flash

    besides, apart from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IUrlHelper
    -1.00
     EconPapers
    -0.92
    TagHelper
    -0.78
    enderror
    -0.76
    #+#
    -0.74
    BibitemShut
    -0.70
     otomatig
    -0.70
     AssemblyCompany
    -0.70
    Personensuche
    -0.69
    "}")
    -0.67
    POSITIVE LOGITS
     besides
    2.68
    besides
    2.43
     aside
    2.06
     apart
    2.00
     selain
    1.97
    Besides
    1.97
     Besides
    1.79
     кроме
    1.77
    apart
    1.72
     além
    1.69
    Activations Density 0.760%

    No Known Activations