© 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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12724
    Prev
    Next
    INDEX
    Explanations

    descriptive language related to beautiful natural landscapes and beaches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hive
    -0.44
    قد
    -0.43
    forestry
    -0.42
    arp
    -0.40
    花板
    -0.39
    ByExample
    -0.39
    uaire
    -0.38
    हार
    -0.38
    aculture
    -0.37
     renovables
    -0.37
    POSITIVE LOGITS
     beach
    1.40
     sandy
    1.38
     beaches
    1.34
     sands
    1.26
     sand
    1.21
    beach
    1.17
     sabbia
    1.11
     BEACH
    1.04
    Beach
    1.01
     spiaggia
    0.99
    Activations Density 0.044%

    No Known Activations