© 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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 15198
    Prev
    Next
    INDEX
    Explanations

    terms related to communication and its effectiveness

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

    "communication"

    np_acts-logits-general · gemini-2.0-flash

    communication skills and systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.72
     imageNamed
    -0.67
     WaitForSeconds
    -0.64
     Xunit
    -0.63
    mybatisplus
    -0.61
     ModelExpression
    -0.61
     estimés
    -0.59
     viewType
    -0.58
     تضيفلها
    -0.58
     verily
    -0.58
    POSITIVE LOGITS
     communication
    1.53
     communications
    1.43
     Communication
    1.26
     communic
    1.23
     communicative
    1.22
     communicating
    1.20
    Communication
    1.20
     COMMUNIC
    1.19
     COMMUNICATION
    1.17
     communicate
    1.16
    Activations Density 0.098%

    No Known Activations