© 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. 7353
    Prev
    Next
    INDEX
    Explanations

    sequences or events in a series

    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
    814
    +0.13
    0.5%
    1325
    +0.12
    0.5%
    1124
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1872
    +0.13
    0.02
    689
    +0.12
    0.02
    1044
    +0.11
    0.02
    Negative Logits
     PLWABN
    -0.54
    Pod
    -0.49
     Pod
    -0.47
     hotell
    -0.46
     Dum
    -0.45
    vaného
    -0.45
     Mier
    -0.45
     Bras
    -0.44
     milla
    -0.44
    kig
    -0.43
    POSITIVE LOGITS
     sequence
    1.38
    sequence
    1.35
     sequences
    1.32
     Sequence
    1.30
    Sequence
    1.25
     seq
    1.23
    sequences
    1.16
    seq
    1.13
     Sequences
    1.12
     SEQUENCE
    1.05
    Activations Density 0.117%

    No Known Activations