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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 5761
    Prev
    Next
    INDEX
    Explanations

    phrases related to security devices and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.78
    fjspx
    -0.63
     nahilalakip
    -0.52
    Архівовано
    -0.50
    sauce
    -0.49
     malattie
    -0.48
     inhalation
    -0.46
     radiador
    -0.46
     chopsticks
    -0.45
     khăn
    -0.44
    POSITIVE LOGITS
     alarm
    1.41
     security
    1.23
     alarms
    1.21
     Alarm
    1.21
    alarm
    1.09
     surveillance
    1.07
     Security
    1.05
    Alarm
    1.05
     CCTV
    1.03
     alarma
    1.01
    Activations Density 0.208%

    No Known Activations