© 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. 2408
    Prev
    Next
    INDEX
    Explanations

    technical elements related to software and networking configurations

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

    technical and system-related metadata like version numbers, software names, and system configurations.

    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
     CHARACTERS
    -0.44
     kazi
    -0.39
    LiveData
    -0.38
    fattning
    -0.38
     actuaciones
    -0.38
    tss
    -0.37
    characters
    -0.36
     clase
    -0.36
     Hivatalos
    -0.36
    schedule
    -0.36
    POSITIVE LOGITS
     AssemblyCulture
    0.60
     AssemblyCompany
    0.59
    SequentialGroup
    0.59
     AssemblyVersion
    0.54
    ]=>
    0.53
     Wicidata
    0.53
    userAgent
    0.53
    bootstrapcdn
    0.51
    execSQL
    0.51
    GeneratedCode
    0.50
    Activations Density 0.210%

    No Known Activations