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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 7895
    Prev
    Next
    INDEX
    Explanations

    references and external links in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens preceding website or profile

    np_acts-logits-general · gemini-2.0-flash

    website profile .com

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </em>
    -0.54
    </h6>
    -0.48
    </h5>
    -0.48
    Enllaces
    -0.44
    );*/
    -0.43
     ***/
    -0.43
    </u>
    -0.42
     Pixabay
    -0.41
     Brid
    -0.41
     Bri
    -0.40
    POSITIVE LOGITS
    EndContext
    0.76
    rungsseite
    0.71
    tagHelperRunner
    0.69
    存于互联网档案馆
    0.65
     MainAxisSize
    0.60
     مشين
    0.59
    новниш
    0.56
     plufieurs
    0.53
     ainfi
    0.51
     wikipagina
    0.50
    Activations Density 0.107%

    No Known Activations