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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 14748
    Prev
    Next
    INDEX
    Explanations

    technical terms and elements related to server configurations

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

    domain names and hostnames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.48
    adpleegd
    -0.45
     Romans
    -0.44
    tanooga
    -0.43
     beno
    -0.40
    ibatis
    -0.40
     encouraging
    -0.40
     bege
    -0.39
     gre
    -0.39
     сх
    -0.38
    POSITIVE LOGITS
     AssemblyCompany
    0.77
    HostException
    0.62
    URLException
    0.62
     şirket
    0.60
     صوتيه
    0.59
    itename
    0.57
    域名
    0.55
    ServerName
    0.52
    hostname
    0.52
    OGND
    0.52
    Activations Density 0.025%

    No Known Activations