© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 8247
    Prev
    Next
    INDEX
    Explanations

    aspects of storytelling related to world-building and character dynamics

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

    Preceding tokens before "in," "that," "are," or "diversity"

    np_acts-logits-general · gemini-2.0-flash

    diversity questionnaire

    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
     then
    -0.49
     Entonces
    -0.48
     entonces
    -0.43
     oppure
    -0.42
    uvwxyz
    -0.42
    Autoritní
    -0.41
     pertenece
    -0.40
    aussi
    -0.40
     belongs
    -0.40
     pertence
    -0.40
    POSITIVE LOGITS
     initWithFrame
    0.52
    %)$
    0.51
    Nonnull
    0.49
    Rhestr
    0.49
    Aside
    0.48
    XmlAccessorType
    0.48
     insofar
    0.48
    ofar
    0.47
    Whilst
    0.47
     variously
    0.46
    Activations Density 0.508%

    No Known Activations