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. 6-GEMMASCOPE-RES-16K
    6. 6182
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'T' along with associated numeric or date-like values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bourgoin
    -0.71
    存于互联网档案馆
    -0.62
    RenderAtEndOf
    -0.58
    Kapcsolódó
    -0.56
     بها
    -0.53
    Amicalement
    -0.52
     davon
    -0.51
    SerializeField
    -0.49
     PLWABN
    -0.48
     Administrativna
    -0.47
    POSITIVE LOGITS
    AddTagHelper
    0.78
    tagHelperRunner
    0.77
    webElementXpaths
    0.67
    AutoScaleMode
    0.63
    UnusedPrivate
    0.62
     midnight
    0.57
    NUMX
    0.55
     Else
    0.55
    ClientSize
    0.55
    IInterface
    0.55
    Activations Density 0.078%

    No Known Activations