© 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. 2-GEMMASCOPE-RES-16K
    6. 13502
    Prev
    Next
    INDEX
    Explanations

    CSS properties and values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    0
    -0.46
    1
    -0.45
    ↵
    -0.43
    .
    -0.42
    (
    -0.38
    ↵↵
    -0.37
    </
    -0.37
    8
    -0.35
    9
    -0.34
    4
    -0.34
    POSITIVE LOGITS
     myſelf
    1.63
     queſta
    1.56
     houſe
    1.55
     ſta
    1.54
     $_(
    1.54
     pleaſure
    1.52
     purpoſe
    1.47
    MigrationBuilder
    1.46
    ſelf
    1.45
     Majefty
    1.45
    Activations Density 0.572%

    No Known Activations