© 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. 4070
    Prev
    Next
    INDEX
    Explanations

    the verb "went"

    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
    1013
    +0.13
    0.4%
    1978
    +0.08
    0.2%
    946
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    251
    +0.13
    0.05
    1921
    +0.08
    0.04
    405
    +0.07
    0.04
    Negative Logits
     sappi
    -1.06
     Ottobre
    -1.04
     vola
    -1.00
     Luglio
    -0.99
     ladri
    -0.97
     ordina
    -0.96
     minimalis
    -0.96
     vogli
    -0.94
     uhr
    -0.92
     sement
    -0.89
    POSITIVE LOGITS
     to
    0.63
     visit
    0.60
    Datuak
    0.59
     back
    0.59
     into
    0.57
     visiting
    0.54
     esternos
    0.53
     alone
    0.52
    bewerken
    0.51
     go
    0.51
    Activations Density 0.269%

    No Known Activations