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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 13467
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the concept of 'taking' or 'taken'

    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
     wikipagina
    -0.77
     ihop
    -0.74
     stället
    -0.74
    ++]=
    -0.71
     stiefel
    -0.70
    antara
    -0.69
     antaranya
    -0.69
    Subclass
    -0.69
     Parcelable
    -0.68
    warnai
    -0.68
    POSITIVE LOGITS
     taken
    1.31
     seen
    1.24
     flown
    1.19
     Seen
    1.15
    seen
    1.12
    taken
    1.08
     Taken
    1.07
    Seen
    1.07
    Taken
    1.04
     shown
    1.03
    Activations Density 0.094%

    No Known Activations