© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 9441
    Prev
    Next
    INDEX
    Explanations

    terms related to genomic data processing and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TypedDataSet
    -0.57
    ChildScrollView
    -0.46
    сшта
    -0.45
    SequentialGroup
    -0.45
    yearly
    -0.42
     invokingState
    -0.42
    Kariera
    -0.42
    الدراسه
    -0.41
     festi
    -0.41
    OrNil
    -0.40
    POSITIVE LOGITS
     reads
    0.79
     Reads
    0.67
     read
    0.64
    reads
    0.60
    Reads
    0.60
     sequencing
    0.60
     alignment
    0.52
     alignments
    0.51
     Read
    0.50
     quality
    0.49
    Activations Density 1.329%

    No Known Activations