© 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. 3-GEMMASCOPE-RES-16K
    6. 8049
    Prev
    Next
    INDEX
    Explanations

    references to animals, particularly those related to mythical creatures and specific species like tigers and elephants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hinweg
    -0.44
     PACE
    -0.42
     })}
    -0.42
     PMI
    -0.38
    ']],
    -0.37
     TLC
    -0.36
    Shea
    -0.36
     PPA
    -0.36
     dụng
    -0.36
    )。
    -0.36
    POSITIVE LOGITS
     elephant
    1.56
     monkey
    1.47
     wolf
    1.44
     rabbit
    1.42
     shark
    1.41
     tiger
    1.35
     lion
    1.34
    elephant
    1.31
     dragon
    1.31
     crocodile
    1.30
    Activations Density 0.386%

    No Known Activations