© 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. 4424
    Prev
    Next
    INDEX
    Explanations

    phrases related to charitable actions and humanitarian efforts

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

    Prepositions and action verbs

    np_acts-logits-general · gemini-2.0-flash

    for patterns, do a, obtain consistent

    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
     lecz
    -0.57
     tačiau
    -0.53
     tevens
    -0.50
     gdyż
    -0.47
     אך
    -0.46
    早已
    -0.46
     nemlig
    -0.45
     "
    -0.44
     poichè
    -0.43
     „
    -0.43
    POSITIVE LOGITS
    basically
    0.77
     somebody
    0.77
    somebody
    0.77
    Basically
    0.75
     basically
    0.73
     gonna
    0.72
     kind
    0.72
     stuff
    0.71
    Somebody
    0.71
     really
    0.69
    Activations Density 0.666%

    No Known Activations