© 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. 5010
    Prev
    Next
    INDEX
    Explanations

    URLs and computer code snippets

    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
    876
    +0.15
    0.4%
    1403
    +0.10
    0.3%
    453
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    760
    +0.15
    0.02
    876
    +0.10
    -0.00
    686
    +0.09
    0.02
    Negative Logits
    Nå
    -0.58
    Trat
    -0.52
    problema
    -0.52
    Från
    -0.52
    Río
    -0.52
    srcs
    -0.50
    És
    -0.50
    Varför
    -0.49
    Estima
    -0.49
    ]){
    -0.49
    POSITIVE LOGITS
     bonjour
    1.19
     blos
    1.18
     milano
    1.17
     paula
    1.14
     !...
    1.13
     ciao
    1.13
     nutr
    1.12
     pollut
    1.12
     inder
    1.12
     michelin
    1.11
    Activations Density 0.097%

    No Known Activations