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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4006
    Prev
    Next
    INDEX
    Explanations

    mentions of locations or names including "Bay."

    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
    805
    +0.17
    0.7%
    1350
    +0.15
    0.7%
    506
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    805
    +0.17
    0.03
    506
    +0.15
    0.02
    1472
    +0.15
    0.02
    Negative Logits
    PerformLayout
    -0.57
     StringTokenizer
    -0.54
    thalene
    -0.53
    LLocation
    -0.52
     nonatomic
    -0.48
    ConverterFactory
    -0.48
    marginHorizontal
    -0.46
    блиоте
    -0.46
    InvalidProtocol
    -0.45
    alignSelf
    -0.45
    POSITIVE LOGITS
     Bay
    1.40
    Bay
    1.39
     bay
    1.34
    bay
    1.28
     BAY
    1.24
    BAY
    1.18
     bays
    1.01
     Bays
    0.97
     Bayley
    0.90
     Bayard
    0.90
    Activations Density 0.065%

    No Known Activations