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. 23-GEMMASCOPE-RES-16K
    6. 11303
    Prev
    Next
    INDEX
    Explanations

    elements related to web application structure and data manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )}</
    -0.67
    hyrchwyd
    -0.65
    })}$
    -0.64
    )])
    -0.64
    )})
    -0.62
    )');
    -0.59
    }])
    -0.58
    ')")
    -0.58
    ">)</
    -0.58
    saraba
    -0.57
    POSITIVE LOGITS
     تضيفلها
    0.63
    WithIdentifier
    0.56
     '\\;'
    0.54
    Erreferentziak
    0.54
    uttgart
    0.54
    توضیحات
    0.52
    存于互联网档案馆
    0.52
    indd
    0.51
    ForValue
    0.50
     offend
    0.49
    Activations Density 0.584%

    No Known Activations