Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 14956
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "out" and its various forms in the context of sending or distributing information or alerts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.72
     חיצוניים
    -0.60
     Roskov
    -0.59
     Réponses
    -0.54
    Geplaatst
    -0.54
     JpaRepository
    -0.51
    glTranslatef
    -0.50
    Население
    -0.49
    ExtendWith
    -0.49
     giustizia
    -0.48
    POSITIVE LOGITS
     ब्रेकडाउन
    0.64
     فريبيس
    0.60
     :\
    0.59
    amation
    0.59
    </b>
    0.58
     Hilde
    0.57
     AttributeSet
    0.56
    achuca
    0.56
     Tapatalk
    0.56
     للمعارف
    0.55
    Activations Density 0.128%

    No Known Activations