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

    Neuronpedia

    Jacobian LensNEW
    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. 11355
    Prev
    Next
    INDEX
    Explanations

    quantitative information and statistics

    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
    776
    +0.12
    0.3%
    184
    +0.11
    0.3%
    1042
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    776
    +0.12
    0.06
    143
    +0.11
    0.05
    792
    +0.11
    0.03
    Negative Logits
     utop
    -1.29
     solidar
    -1.18
     marte
    -1.17
     poliester
    -1.16
     poliuret
    -1.12
     ananas
    -1.11
     meras
    -1.10
     sement
    -1.08
     patate
    -1.08
     elek
    -1.08
    POSITIVE LOGITS
     are
    0.79
     impelled
    0.77
     were
    0.77
     unspeak
    0.76
     unavoid
    0.74
     is
    0.70
     went
    0.70
     tolerably
    0.70
     was
    0.69
     had
    0.69
    Activations Density 0.238%

    No Known Activations