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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 17-GEMMASCOPE-RES-16K
    6. 9121
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their patterns in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -0.90
    beelden
    -0.58
    antaranya
    -0.55
    المشاركات
    -0.55
     và
    -0.53
    værende
    -0.51
     toepassing
    -0.51
     or
    -0.48
    <bos>
    -0.48
    以及
    -0.47
    POSITIVE LOGITS
     nahilalakip
    1.08
    contentLoaded
    0.78
     ddelweddau
    0.73
    /**
    0.68
    PreferredItem
    0.66
    λοι
    0.65
    bkz
    0.65
    imedia
    0.65
    albeit
    0.63
    batore
    0.62
    Activations Density 0.509%

    No Known Activations