© 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. 1008
    Prev
    Next
    INDEX
    Explanations

    mentions of specific football players and potential transfers

    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
    1042
    +0.12
    0.4%
    344
    +0.09
    0.2%
    392
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1501
    +0.12
    0.04
    392
    +0.09
    0.03
    632
    +0.08
    0.03
    Negative Logits
     embodi
    -1.04
     swarovski
    -0.87
     anhyd
    -0.86
     nephe
    -0.84
     suscep
    -0.83
     friable
    -0.80
     hairc
    -0.80
     milano
    -0.80
     impractica
    -0.79
     Ename
    -0.79
    POSITIVE LOGITS
     kosme
    0.81
     minimalis
    0.77
     kompati
    0.74
     konkre
    0.73
     kön
    0.68
     panik
    0.67
     praktik
    0.67
     menyen
    0.66
     bera
    0.66
     kompak
    0.66
    Activations Density 0.355%

    No Known Activations