© 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. 15-GEMMASCOPE-RES-16K
    11. 8831
    Prev
    Next
    INDEX
    Explanations

    themes related to emotional depth and complex relationships in storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.54
     Stelle
    -0.48
    mlung
    -0.45
     względem
    -0.45
    glVertex
    -0.45
     davon
    -0.44
     endroits
    -0.43
    cayaan
    -0.43
     håll
    -0.43
    mybatisplus
    -0.43
    POSITIVE LOGITS
     confines
    0.72
     invokingState
    0.69
     glories
    0.66
    IUrlHelper
    0.63
    XmlAccessType
    0.63
     delights
    0.60
     workings
    0.59
    ValueStyle
    0.58
     antics
    0.58
    iteritems
    0.56
    Activations Density 0.293%

    No Known Activations