© 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-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 8350
    Prev
    Next
    INDEX
    Explanations

    references to specific subjects or entities within a broader context

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

    Follows "the" or "my" and precedes a noun

    np_acts-logits-general · gemini-2.0-flash

    the followed by noun

    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
    awtextra
    -0.42
     unique
    -0.40
     CURIAM
    -0.39
    出版年
    -0.39
     уника
    -0.38
    freopen
    -0.37
    如何在
    -0.36
     Meso
    -0.35
    Condol
    -0.35
    就会
    -0.35
    POSITIVE LOGITS
     margins
    0.51
    ंदीखरीदारी
    0.49
     turnout
    0.48
     amounts
    0.47
     prijzen
    0.47
    tagext
    0.46
     архивлан
    0.46
     conditions
    0.46
    ########.
    0.46
     outlay
    0.45
    Activations Density 0.683%

    No Known Activations