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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12683
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific measurements and properties, particularly in physics and chemistry contexts

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

    Elements from the periodic table

    np_acts-logits-general · gemini-2.0-flash

    helium, selen, sek

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     للاسماء
    -0.73
     doInBackground
    -0.53
     Knopf
    -0.50
     kaynağından
    -0.50
    WriteTagHelper
    -0.49
     numberWith
    -0.49
    indale
    -0.49
    สือ
    -0.49
     kasarigan
    -0.48
    がり
    -0.48
    POSITIVE LOGITS
    selben
    0.60
    eb
    0.55
    ServletException
    0.54
    eck
    0.54
    ecke
    0.54
    ew
    0.53
    ec
    0.53
    ech
    0.53
     fédé
    0.52
     vété
    0.51
    Activations Density 2.040%

    No Known Activations