© 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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14229
    Prev
    Next
    INDEX
    Explanations

    discussions about advantages and disadvantages in decision-making processes

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

    Advantages and disadvantages

    np_acts-logits-general · gemini-2.0-flash

    pros and cons

    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
     AssemblyTitle
    -0.60
    rungsseite
    -0.53
    oneofs
    -0.51
    BindingSource
    -0.50
    BufferException
    -0.50
     myſelf
    -0.50
    yntaxException
    -0.49
    onomía
    -0.49
     Eſ
    -0.48
     minde
    -0.46
    POSITIVE LOGITS
     avantages
    0.61
     advantages
    0.61
     voordelen
    0.61
     Advantages
    0.55
     benefits
    0.52
    Advantages
    0.50
    advantages
    0.50
     Benefits
    0.47
     ventajas
    0.46
     avantaj
    0.45
    Activations Density 0.549%

    No Known Activations