© 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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 78051
    Prev
    Next
    INDEX
    Explanations

    the term "svd" and its variations, which likely relates to singular value decomposition in mathematical or computational contexts

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

    reserved fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageOf
    -0.63
    ьаж
    -0.57
     препратки
    -0.57
     SwitchCompat
    -0.56
    AndEndTag
    -0.55
     fallu
    -0.52
     BrowserModule
    -0.50
    rungsseite
    -0.49
     NUKAT
    -0.48
    InputBorder
    -0.48
    POSITIVE LOGITS
     reserve
    1.74
     Reserve
    1.53
    reserve
    1.48
    Reserve
    1.47
     reserved
    1.45
     reservation
    1.41
     RESERVE
    1.39
     reserv
    1.34
     Reserved
    1.34
     reserves
    1.33
    Activations Density 0.022%

    No Known Activations