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. 13-GEMMASCOPE-RES-16K
    6. 71
    Prev
    Next
    INDEX
    Explanations

    expressions of intense emotions and personal declarations

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

    first-person pronouns, often indicating statements or expressions of personal experience or involvement.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ysty
    -0.51
    њи
    -0.43
    PageNumber
    -0.41
    тор
    -0.40
    ket
    -0.40
    Tal
    -0.40
     Neu
    -0.40
    pos
    -0.40
     Her
    -0.39
     valign
    -0.39
    POSITIVE LOGITS
    uxxxx
    0.87
     AssemblyCulture
    0.87
    principalTable
    0.77
    TextWatcher
    0.75
    цездатний
    0.75
    InstanceState
    0.71
    esgue
    0.71
    tymologie
    0.70
     TextAlign
    0.70
     Bearer
    0.69
    Activations Density 0.116%

    No Known Activations