© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 5605
    Prev
    Next
    INDEX
    Explanations

    HTML attribute assignments and their values

    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
     RemoteException
    -0.73
    '.$
    -0.71
    ();*/
    -0.66
    böz
    -0.65
    lossians
    -0.64
    displayquote
    -0.62
    ない
    -0.60
    );*/
    -0.58
     Camin
    -0.58
    ないので
    -0.58
    POSITIVE LOGITS
    AndEndTag
    0.93
    ="
    0.93
    MessageTagHelper
    0.86
     مُعرِّف
    0.86
     Audiodateien
    0.85
     préoccup
    0.82
    <%=
    0.80
     EconPapers
    0.77
     Carmichael
    0.74
    ="@+
    0.74
    Activations Density 0.153%

    No Known Activations