© 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. 2278
    Prev
    Next
    INDEX
    Explanations

    elements related to systematic assessment or review

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

    academic or legal documents discussing professional achievements and procedural details.

    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
     يتيمه
    -1.16
    principalColumn
    -1.06
     snippetHide
    -1.03
    adaptiveStyles
    -0.97
    fromnode
    -0.93
     betweenstory
    -0.93
    PreferredItem
    -0.91
    parsedMessage
    -0.90
     ujednoznacz
    -0.88
    niſſe
    -0.87
    POSITIVE LOGITS
    Finally
    0.50
    <eos>
    0.50
     Finally
    0.45
     finally
    0.44
    Overall
    0.43
    <h3>
    0.41
    5
    0.41
    1
    0.40
    The
    0.39
    2
    0.39
    Activations Density 0.027%

    No Known Activations