© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8658
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to scientific methodologies and evaluations

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

    clauses or phrases that indicate conditions or qualifications in academic or technical text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
     Estructura
    -0.26
    客
    -0.26
     przyczyn
    -0.26
    over
    -0.25
    Clickable
    -0.25
    tragung
    -0.24
     quidem
    -0.24
     znan
    -0.24
    trainable
    -0.24
    once
    -0.23
    POSITIVE LOGITS
     ujednoznacz
    0.73
    <unused14>
    0.71
    <unused68>
    0.71
    <unused52>
    0.71
    <unused21>
    0.71
    <unused16>
    0.71
    <unused8>
    0.71
    <unused79>
    0.70
    <unused74>
    0.70
    [@BOS@]
    0.70
    Activations Density 0.703%

    No Known Activations