© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 4198
    Prev
    Next
    INDEX
    Explanations

    quotes and dialogues within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.30
    1.1%
    381
    +0.18
    0.7%
    906
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    381
    +0.30
    0.05
    2044
    +0.18
    0.06
    162
    +0.10
    0.05
    Negative Logits
     chery
    -1.14
     leonardo
    -1.14
     paula
    -1.13
    ⓧ
    -1.11
     gabriel
    -1.10
     claudia
    -1.09
     gabri
    -1.08
     gtr
    -1.08
     swarovski
    -1.06
     stefan
    -1.05
    POSITIVE LOGITS
     disiplin
    0.61
     ajustable
    0.60
    SceneManagement
    0.57
     conversa
    0.55
     I
    0.53
     comis
    0.53
     Jefe
    0.53
     panik
    0.52
     plastik
    0.52
    conio
    0.51
    Activations Density 0.360%

    No Known Activations