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. 3842
    Prev
    Next
    INDEX
    Explanations

    the term "only," indicating exclusivity or limitation

    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
    })+\
    -0.66
    Mila
    -0.58
    报
    -0.56
    >--}}
    -0.55
    Facades
    -0.53
    las
    -0.52
     Mila
    -0.52
    {}\
    -0.51
    yla
    -0.51
    TimeTo
    -0.50
    POSITIVE LOGITS
     only
    1.30
    only
    1.26
    ONLY
    1.16
     ONLY
    1.03
     seulement
    0.98
    Only
    0.97
     Only
    0.94
     uniquement
    0.92
     seuls
    0.88
     numai
    0.86
    Activations Density 0.184%

    No Known Activations