© 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
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2656
    Prev
    Next
    INDEX
    Explanations

    instructions and actions related to configuration and connectivity

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

    technical instructions or step-by-step processes, especially related to technology and product usage.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    AddTagHelper
    -0.68
    InjectAttribute
    -0.66
     betweenstory
    -0.65
     فريبيس
    -0.61
    featureID
    -0.60
    WriteBarrier
    -0.59
     GenerationType
    -0.59
    #+#
    -0.57
    رشف
    -0.55
    PickerController
    -0.55
    POSITIVE LOGITS
     simply
    0.53
    simply
    0.51
     simple
    0.48
     wystarczy
    0.47
     effortless
    0.47
    Simply
    0.45
     effortlessly
    0.44
     tinggal
    0.44
    只需要
    0.44
    einf
    0.44
    Activations Density 0.176%

    No Known Activations