© 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. 16280
    Prev
    Next
    INDEX
    Explanations

    specific references to investigations and administrative contexts

    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
     ſta
    -0.65
     ſte
    -0.60
     تضيفلها
    -0.53
     ſur
    -0.52
     ſch
    -0.52
     ſp
    -0.51
    ApiProperty
    -0.49
    WriteTagHelper
    -0.49
     ſche
    -0.48
    ፩
    -0.48
    POSITIVE LOGITS
    uxxxx
    0.59
    antaine
    0.41
    UserScript
    0.36
     yanı
    0.36
    Hrsg
    0.36
     din
    0.35
    EDEFAULT
    0.35
    bkz
    0.34
    是
    0.34
    parsedMessage
    0.33
    Activations Density 0.676%

    No Known Activations