© 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. 14376
    Prev
    Next
    INDEX
    Explanations

    statements indicating the purpose or aim of a project or study

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    msgTypes
    -0.84
     ModelExpression
    -0.78
    Diweddarwch
    -0.75
     nakalista
    -0.75
     témoig
    -0.75
    ſſung
    -0.75
    <unused43>
    -0.74
    <unused3>
    -0.74
     <=",
    -0.74
    <unused8>
    -0.74
    POSITIVE LOGITS
     aim
    1.15
     purpose
    1.02
     aims
    0.98
     goal
    0.96
     intention
    0.90
     aiming
    0.88
    objectif
    0.84
     objectif
    0.82
    的目的
    0.82
     objetivo
    0.82
    Activations Density 0.267%

    No Known Activations