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. 2-GEMMASCOPE-RES-16K
    6. 2144
    Prev
    Next
    INDEX
    Explanations

    words related to abstract concepts, particularly those ending in 'ity'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cima
    -0.49
    ))/(
    -0.49
    simov
    -0.48
    }}],
    -0.46
    JsonValue
    -0.46
     Refuge
    -0.45
    imoto
    -0.45
     problema
    -0.45
    كير
    -0.45
    script
    -0.44
    POSITIVE LOGITS
    ities
    0.90
    ArgsConstructor
    0.84
     FetchType
    0.83
    ITY
    0.83
    ality
    0.80
    ity
    0.77
    idade
    0.76
    idad
    0.75
    enskap
    0.70
     متعلقه
    0.68
    Activations Density 2.383%

    No Known Activations