© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 7642
    Prev
    Next
    INDEX
    Explanations

    sporting event outcomes and scores

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1978
    +0.13
    0.4%
    906
    +0.11
    0.3%
    1905
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    523
    +0.13
    0.03
    1905
    +0.11
    0.02
    1804
    +0.10
    0.03
    Negative Logits
     embodi
    -0.98
     swarovski
    -0.98
     [''
    -0.80
     unwarran
    -0.80
     fince
    -0.80
     reft
    -0.79
     hairc
    -0.79
     tupperware
    -0.78
     parch
    -0.77
     linden
    -0.76
    POSITIVE LOGITS
     kayo
    0.67
     saurait
    0.62
    UITableViewCell
    0.57
     lamang
    0.53
    hamdu
    0.52
    ImageBackground
    0.51
    JsonResponse
    0.49
     potest
    0.48
     mène
    0.48
     habet
    0.48
    Activations Density 0.140%

    No Known Activations