© 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. 4388
    Prev
    Next
    INDEX
    Explanations

    patterns and structures in numeric and statistical data

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

    numerical or mathematical expressions and scientific notation.

    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
     surla
    -0.54
    IBOutlet
    -0.48
    XmlRootElement
    -0.48
     IBOutlet
    -0.46
    IVEREF
    -0.44
    ItemLayout
    -0.43
    CascadeType
    -0.43
    CloseOperation
    -0.42
    Tikang
    -0.42
    })->
    -0.41
    POSITIVE LOGITS
    Notae
    0.67
     تانيه
    0.59
    +#+
    0.53
    hoeddwyd
    0.51
     contextLoads
    0.50
    OGND
    0.49
    GeoNames
    0.48
     AssemblyCompany
    0.48
     betweenstory
    0.46
    writeFieldEnd
    0.45
    Activations Density 1.391%

    No Known Activations