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. 13337
    Prev
    Next
    INDEX
    Explanations

    instances of decision-making, assessment of quality, and validation of authority or claims

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

    Follows prepositions and conjunction "that"

    np_acts-logits-general · gemini-2.0-flash

    success and outcomes

    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
     BoxFit
    -0.33
    DebuggerStep
    -0.31
     umge
    -0.30
     voilà
    -0.29
    withOpacity
    -0.27
    ::_('
    -0.27
     Fuentes
    -0.27
     volando
    -0.27
     alguien
    -0.26
    mrow
    -0.26
    POSITIVE LOGITS
    ſelf
    0.71
     للاسماء
    0.59
     isSuccess
    0.59
     queſta
    0.58
    phazard
    0.57
    之所以
    0.56
    ſelves
    0.55
     myſelf
    0.55
    ſchaft
    0.55
     AssemblyCompany
    0.54
    Activations Density 1.020%

    No Known Activations