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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 12526
    Prev
    Next
    INDEX
    Explanations

    elements associated with comparisons, especially those involving qualifiers and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddHtmlAttribute
    -0.74
    ﹠
    -0.65
     propOrder
    -0.64
    ‍♀️
    -0.63
    (',')
    -0.60
    Portale
    -0.60
     gyhoeddwyd
    -0.59
     كومونز
    -0.59
    InitVars
    -0.58
     AppCompatTheme
    -0.58
    POSITIVE LOGITS
     виправивши
    0.64
     polaire
    0.62
     مشين
    0.58
     snippetHide
    0.57
    σθαι
    0.56
    ioutil
    0.55
    Skocz
    0.53
     stronger
    0.53
    awaiter
    0.52
     resourceCulture
    0.52
    Activations Density 0.457%

    No Known Activations