© 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. 3997
    Prev
    Next
    INDEX
    Explanations

    phrases related to home appliance services and tax-related accounts

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

    Company-related services or offerings

    np_acts-logits-general · gemini-2.0-flash

    company services

    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
     libremente
    -0.40
     invloed
    -0.36
     rightly
    -0.36
     jurk
    -0.34
     incertidumbre
    -0.34
     antemano
    -0.34
     navideña
    -0.33
     Gewerks
    -0.33
     stappen
    -0.32
    bleven
    -0.32
    POSITIVE LOGITS
     services
    0.70
     turnkey
    0.67
    services
    0.66
     customized
    0.60
     consultancy
    0.58
     custom
    0.58
     consulting
    0.58
     consultations
    0.56
     Services
    0.56
     AssemblyCompany
    0.56
    Activations Density 0.233%

    No Known Activations