© 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. 0-GEMMASCOPE-RES-16K
    6. 7241
    Prev
    Next
    INDEX
    Explanations

    terms related to sampling and samples in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /$',
    -0.42
     ligiloj
    -0.42
     care
    -0.40
    windig
    -0.39
     usual
    -0.39
    คง
    -0.38
     Verkehrs
    -0.38
    mbic
    -0.38
     Slots
    -0.37
    uarine
    -0.36
    POSITIVE LOGITS
     sam
    1.11
     sampling
    1.02
    sam
    0.99
     Sampling
    0.98
    Sam
    0.95
     Sam
    0.94
     sampler
    0.92
    SAM
    0.90
    Sampler
    0.90
    sampler
    0.90
    Activations Density 1.722%

    No Known Activations