© 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 EvalsExportsinterp-engineNEWAPI 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. 16237
    Prev
    Next
    INDEX
    Explanations

    references to news articles and interviews

    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
    1777
    +0.14
    0.5%
    32
    +0.12
    0.4%
    1472
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1777
    +0.14
    0.04
    1370
    +0.12
    0.04
    781
    +0.11
    0.03
    Negative Logits
    lántico
    -0.52
    ⏪
    -0.51
    metido
    -0.51
     uska
    -0.51
     WQS
    -0.50
     esternos
    -0.50
     gynhyrchwyd
    -0.49
    χρι
    -0.49
     OMIT
    -0.48
    biamo
    -0.48
    POSITIVE LOGITS
     unspeak
    1.17
     disagre
    1.13
     Confu
    1.12
     encomp
    1.12
     shenan
    1.11
     News
    1.09
     reluct
    1.06
     indestru
    1.06
     depic
    1.05
     inconce
    1.05
    Activations Density 0.051%

    No Known Activations