© 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. 3976
    Prev
    Next
    INDEX
    Explanations

    phrases related to safety, suitability, and quality assessments of products or materials

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

    Good, safe, suitable, or adequate

    np_acts-logits-general · gemini-2.0-flash

    suitability for purpose

    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
     MainAxisSize
    -0.47
    TypedDataSet
    -0.45
    MessageOf
    -0.40
     GetEnumerator
    -0.37
    CrossRef
    -0.37
     abstrait
    -0.35
    PostBack
    -0.35
    帖最后由
    -0.35
     referenties
    -0.35
     Karlsruhe
    -0.35
    POSITIVE LOGITS
     usable
    1.36
     playable
    1.07
    usable
    1.03
     usability
    0.97
     unusable
    0.96
     habitable
    0.85
     serviceable
    0.85
     edible
    0.84
    playable
    0.81
     workable
    0.78
    Activations Density 0.576%

    No Known Activations