© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 12305
    Prev
    Next
    INDEX
    Explanations

    the beginning of sentences, particularly those that signal new or important ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Auft
    -0.61
    aarrggbb
    -0.57
    ="";
    -0.56
    看起來
    -0.51
    看起来
    -0.50
     formal
    -0.50
    看上去
    -0.49
     anti
    -0.48
    looks
    -0.46
    AutoField
    -0.46
    POSITIVE LOGITS
     estimés
    0.91
     يتيمه
    0.81
    ClientSize
    0.69
    PHeader
    0.66
    脚注の使い方
    0.65
    Geplaatst
    0.64
    yntaxException
    0.62
    MetaObject
    0.61
     Miele
    0.59
    HostException
    0.58
    Activations Density 0.009%

    No Known Activations