© 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. 5148
    Prev
    Next
    INDEX
    Explanations

    Keywords related to self-initiated projects or ventures

    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
    674
    +0.09
    0.2%
    1533
    +0.07
    0.2%
    488
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    638
    +0.09
    0.03
    1415
    +0.07
    0.02
    1685
    +0.07
    0.03
    Negative Logits
     thut
    -1.38
     reluct
    -1.35
     volunte
    -1.35
     increa
    -1.33
     disagre
    -1.33
     Intere
    -1.33
     Middles
    -1.32
     Rine
    -1.31
     depic
    -1.31
     inev
    -1.30
    POSITIVE LOGITS
     independently
    1.11
     independent
    1.06
     self
    1.06
     alone
    0.99
     own
    0.97
    independent
    0.95
    self
    0.94
     tự
    0.92
    Self
    0.90
     solo
    0.90
    Activations Density 0.425%

    No Known Activations