© 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. 5-GEMMASCOPE-RES-16K
    11. 13828
    Prev
    Next
    INDEX
    Explanations

    references to academic grading levels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nantucket
    -0.86
    +#+#
    -0.81
    anskje
    -0.80
    İstinadlar
    -0.75
    },[])
    -0.75
    RTEX
    -0.74
    ucket
    -0.74
    TargetException
    -0.71
     Jörg
    -0.71
     Nusa
    -0.70
    POSITIVE LOGITS
     grade
    2.51
     grades
    2.45
     Grade
    2.40
     GRADE
    2.34
     Grades
    2.30
    Grade
    2.28
    grade
    2.26
    grades
    2.14
    Grades
    2.10
    GRADE
    1.94
    Activations Density 0.067%

    No Known Activations