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. 5452
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to scientific methods and processes

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

    list items followed by punctuation

    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
     AssemblyCulture
    -0.62
    AndEndTag
    -0.56
    Rhestr
    -0.51
    #+#
    -0.47
    endphp
    -0.46
     kaarangay
    -0.46
    MockMvc
    -0.43
     autorytatywna
    -0.43
     GetEnumerator
    -0.43
    ngrx
    -0.42
    POSITIVE LOGITS
    tellen
    0.44
     Ganzen
    0.43
     zase
    0.40
    jména
    0.40
     Fällen
    0.39
     Vereine
    0.39
    transQ
    0.38
     situações
    0.38
     Initiatives
    0.38
    illoin
    0.38
    Activations Density 0.199%

    No Known Activations