© 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. 14593
    Prev
    Next
    INDEX
    Explanations

    mentions of specific sports team names and players in relation to team needs and potential trades

    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
    184
    +0.17
    0.5%
    1253
    +0.13
    0.4%
    137
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.17
    0.03
    184
    +0.13
    0.01
    392
    +0.12
    0.01
    Negative Logits
     particolar
    -0.78
     preghiera
    -0.77
    igenous
    -0.77
    anical
    -0.74
     grazia
    -0.73
     decorazione
    -0.72
    idance
    -0.71
     religione
    -0.71
     onore
    -0.69
     ceramica
    -0.69
    POSITIVE LOGITS
    FTFY
    0.76
    Lmfao
    0.68
     naquele
    0.60
    Slik
    0.59
    Lma
    0.58
    Hahah
    0.58
     kosme
    0.58
    Hilsen
    0.57
    Noice
    0.57
     isolado
    0.57
    Activations Density 0.068%

    No Known Activations