© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 14399
    Prev
    Next
    INDEX
    Explanations

    assertions of personal experience related to evidence and credibility, particularly in the context of legal or social claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -0.68
    ScopeManager
    -0.66
    曖昧さ回避
    -0.65
     Wicidata
    -0.65
     '\\;'
    -0.64
     AssemblyCulture
    -0.64
    AndEndTag
    -0.63
    expandindo
    -0.63
     Bioaccumulative
    -0.63
     otomatig
    -0.62
    POSITIVE LOGITS
     any
    0.67
     anyone
    0.58
     anywhere
    0.57
    任何人
    0.56
     anybody
    0.53
     except
    0.52
     anything
    0.52
     jemals
    0.52
     ANY
    0.52
     żad
    0.51
    Activations Density 0.635%

    No Known Activations