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. 16-GEMMASCOPE-RES-16K
    6. 3070
    Prev
    Next
    INDEX
    Explanations

    phrases related to death and family connections

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

    Comes after "of" or "in" followed by a placename

    np_acts-logits-general · gemini-2.0-flash

    locations after prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lievito
    -0.50
    +#+#
    -0.50
    πέ
    -0.49
    textTheme
    -0.49
    juvant
    -0.46
    vaadin
    -0.45
    Eloquent
    -0.45
    rhein
    -0.45
    oven
    -0.45
    jedis
    -0.44
    POSITIVE LOGITS
    RegistryLite
    0.80
     архивлан
    0.72
    contentLoaded
    0.71
     Савезне
    0.67
     мәкалә
    0.64
     Vikipedi
    0.63
    oredCriteria
    0.63
     ModelExpression
    0.63
    .")]
    0.61
    Хьажоргаш
    0.60
    Activations Density 0.058%

    No Known Activations