© 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. 2510
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal issues, particularly focusing on race and publishing biases

    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
    198
    +0.14
    0.4%
    1385
    +0.13
    0.4%
    1042
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.14
    0.08
    16
    +0.13
    0.07
    704
    +0.10
    0.01
    Negative Logits
     vété
    -1.20
     alliés
    -0.94
     malheureux
    -0.92
     jacques
    -0.91
     créateur
    -0.84
     fua
    -0.83
     monstre
    -0.82
     mères
    -0.81
     impra
    -0.80
     spécialistes
    -0.79
    POSITIVE LOGITS
     staff
    0.84
     personnel
    0.79
     employees
    0.79
     participants
    0.74
     members
    0.70
     individuals
    0.64
     players
    0.64
     founding
    0.63
     occupants
    0.60
     persons
    0.60
    Activations Density 0.721%

    No Known Activations