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. 11-GEMMASCOPE-RES-16K
    6. 13845
    Prev
    Next
    INDEX
    Explanations

    programming constructs and syntax related to method declarations and parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.81
     disambiguazione
    -0.73
    WithIOException
    -0.70
    fromnode
    -0.68
    Démographie
    -0.66
     Diction
    -0.65
     Amen
    -0.64
    Sucesor
    -0.64
     Meto
    -0.62
    village
    -0.62
    POSITIVE LOGITS
    )
    0.64
    __':
    0.58
    ))
    0.55
    ])
    0.54
    ього
    0.54
    |)
    0.53
    RTRS
    0.52
    <bos>
    0.52
    TableHead
    0.51
     ])
    0.51
    Activations Density 0.042%

    No Known Activations