© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10638
    Prev
    Next
    INDEX
    Explanations

    phrases related to biases in research and study design

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

    bias or inaccuracy

    np_acts-logits-general · gemini-2.0-flash

    bias and inaccuracies

    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
    szönöm
    -0.46
    anniversaire
    -0.42
    SBATCH
    -0.41
     ModelExpression
    -0.40
    endphp
    -0.38
     reinforcement
    -0.38
     Consumo
    -0.38
    OGND
    -0.35
    Hozzáférés
    -0.35
    SequentialGroup
    -0.35
    POSITIVE LOGITS
    StructEnd
    0.57
    TagMode
    0.52
     inaccuracies
    0.45
     unreliable
    0.44
     biases
    0.43
     facteurs
    0.42
    ForValue
    0.42
     inaccurate
    0.42
     biased
    0.42
     flawed
    0.40
    Activations Density 1.019%

    No Known Activations