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. 3-GEMMASCOPE-RES-16K
    6. 16227
    Prev
    Next
    INDEX
    Explanations

    phrases indicating necessity or actions to be taken

    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
     resourceCulture
    -0.70
    ########.
    -0.65
     externi
    -0.60
    GrantedAuthority
    -0.58
    AddHtmlAttribute
    -0.58
    tvguidetime
    -0.57
    SpringBootTest
    -0.57
    DotNetBar
    -0.55
    Hochspringen
    -0.54
    RegistryLite
    -0.53
    POSITIVE LOGITS
     때문
    0.83
    RectangleBorder
    0.68
     devrez
    0.67
    $")
    0.65
    ælde
    0.65
     terpaksa
    0.63
     пришлось
    0.63
     \]
    0.60
     zelfs
    0.60
     luego
    0.58
    Activations Density 0.216%

    No Known Activations