© 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. 14877
    Prev
    Next
    INDEX
    Explanations

    dates related to events

    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
    +0.14
    0.4%
    1741
    +0.14
    0.4%
    1978
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    648
    +0.14
    0.06
    499
    +0.14
    0.05
    776
    +0.14
    0.05
    Negative Logits
     withal
    -0.74
     xdrive
    -0.66
     soeur
    -0.64
     adjour
    -0.62
     bonbons
    -0.62
     február
    -0.59
     anteriorly
    -0.59
     tupperware
    -0.59
     shivered
    -0.59
     severally
    -0.58
    POSITIVE LOGITS
     Áng
    0.77
     Darío
    0.76
     akade
    0.65
     Redacción
    0.65
     Mejía
    0.65
     Valentín
    0.65
     monaster
    0.64
     Asunción
    0.64
    Katso
    0.63
     Lázaro
    0.63
    Activations Density 0.130%

    No Known Activations