© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 1402
    Prev
    Next
    INDEX
    Explanations

    terms related to the establishment and implementation of academic programs or institutional reforms

    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
    +0.26
    1.0%
    1778
    +0.11
    0.4%
    752
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1778
    +0.26
    0.04
    1379
    +0.11
    0.03
    16
    +0.11
    0.04
    Negative Logits
    <bos>
    -3.10
     served
    -0.76
     find
    -0.76
     get
    -0.76
     may
    -0.75
     did
    -0.74
     held
    -0.74
     gave
    -0.74
    public
    -0.73
     could
    -0.73
    POSITIVE LOGITS
     stockholm
    1.97
     frankfurt
    1.95
     affor
    1.89
     increa
    1.79
     milf
    1.78
     tramont
    1.78
     bandung
    1.75
     napoli
    1.74
     eiffel
    1.74
     bangkok
    1.74
    Activations Density 0.269%

    No Known Activations