Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 7087
    Prev
    Next
    INDEX
    Explanations

    situations involving crowded or confined spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]--;
    -0.59
    هب
    -0.50
     phantom
    -0.48
     olvido
    -0.47
    éf
    -0.45
    ่อน
    -0.45
    Recovered
    -0.45
    LookAnd
    -0.45
    Recover
    -0.44
    empl
    -0.44
    POSITIVE LOGITS
     claust
    1.17
     confined
    1.02
     cramped
    1.01
     crammed
    0.91
     enclosed
    0.89
     crowded
    0.89
     sardines
    0.88
     tight
    0.86
     packed
    0.85
     crowding
    0.83
    Activations Density 0.209%

    No Known Activations