© 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. 6477
    Prev
    Next
    INDEX
    Explanations

    timestamps and time zones

    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
    2034
    +0.13
    0.4%
    856
    +0.12
    0.3%
    1150
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    300
    +0.13
    0.03
    1819
    +0.12
    0.03
    1538
    +0.11
    0.03
    Negative Logits
     Walkover
    -0.77
     himo
    -0.71
    queryInterface
    -0.71
    +#+#
    -0.71
    velocityX
    -0.67
    AsUp
    -0.63
    ViewFeatures
    -0.61
    astéro
    -0.61
     OFDb
    -0.61
     ModelExpression
    -0.60
    POSITIVE LOGITS
     maneu
    1.26
     unve
    1.16
     ineffec
    1.13
     depic
    1.10
     suscep
    1.10
     disagre
    1.09
     snoopy
    1.08
     strick
    1.06
     impra
    1.05
     reluct
    1.05
    Activations Density 0.087%

    No Known Activations