© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10360
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize assistance or support provided to others

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

    "Help" or "helps"

    np_acts-logits-general · gemini-2.0-flash

    facilitate positive outcomes

    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
     lais
    -0.30
    SequentialGroup
    -0.28
    ArrowToggle
    -0.27
     externi
    -0.27
     into
    -0.26
    cesis
    -0.26
    Descripció
    -0.26
     Réponses
    -0.26
    TIMORE
    -0.25
     ""],
    -0.25
    POSITIVE LOGITS
     facilitate
    0.71
     formulate
    0.68
     motivate
    0.67
    helped
    0.67
    kkue
    0.65
     bring
    0.64
     resolve
    0.64
     establish
    0.63
    fully
    0.63
     make
    0.63
    Activations Density 0.079%

    No Known Activations