Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 9845
    Prev
    Next
    INDEX
    Explanations

    strategies and actions related to effective communication and feedback in organizational settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CanadaChoose
    -0.58
    reportWebVitals
    -0.57
     rospy
    -0.49
    MLLoader
    -0.46
    redited
    -0.46
     BoxFit
    -0.46
    GOTREF
    -0.46
    MockMvc
    -0.45
    ViewInit
    -0.45
    verifyException
    -0.44
    POSITIVE LOGITS
     listening
    0.45
     know
    0.45
     constant
    0.43
     listen
    0.43
     understand
    0.42
     patience
    0.41
     focus
    0.40
     LISTEN
    0.40
     embrace
    0.39
     humble
    0.39
    Activations Density 0.262%

    No Known Activations