© 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. 12224
    Prev
    Next
    INDEX
    Explanations

    locations or proper nouns related to cities

    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
    856
    +0.14
    0.4%
    1013
    +0.14
    0.4%
    227
    +0.12
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    512
    +0.14
    0.07
    227
    +0.14
    0.07
    1965
    +0.12
    0.06
    Negative Logits
     Ottobre
    -0.88
     Luglio
    -0.84
     Giugno
    -0.81
     vogliono
    -0.79
     parteci
    -0.79
     affez
    -0.76
     dicono
    -0.74
     sento
    -0.70
     Settembre
    -0.70
     vogli
    -0.68
    POSITIVE LOGITS
     Gorb
    0.69
     McLaugh
    0.67
     Olof
    0.66
     Punj
    0.66
     Heere
    0.64
     Rine
    0.63
     Vaugh
    0.62
     Advoc
    0.62
     unve
    0.62
     Bengt
    0.61
    Activations Density 0.233%

    No Known Activations