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. 12-GEMMASCOPE-RES-16K
    6. 10044
    Prev
    Next
    INDEX
    Explanations

    mentions of family relationships, particularly focusing on the description of a deceased person and their relatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.60
    principalTable
    -0.59
     ungef
    -0.58
     noDo
    -0.56
     Atlántico
    -0.55
    στή
    -0.54
     obstante
    -0.53
     recul
    -0.51
     ofrecerte
    -0.51
    lıyor
    -0.50
    POSITIVE LOGITS
    Hochspringen
    0.65
    bootstrapcdn
    0.56
     endeavors
    0.52
    webdriver
    0.49
    tvguidetime
    0.48
     itemprop
    0.47
    DoubleQuotes
    0.46
    HostException
    0.46
     Lastly
    0.45
    phology
    0.44
    Activations Density 0.018%

    No Known Activations