© 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. 3306
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or places, particularly in a historical context

    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
    +0.32
    1.3%
    394
    +0.14
    0.6%
    1013
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1317
    +0.32
    0.05
    612
    +0.14
    0.05
    1251
    +0.09
    0.08
    Negative Logits
    <bos>
    -2.14
     intersper
    -1.26
     endow
    -0.96
     disbur
    -0.87
     shenan
    -0.86
     endeavored
    -0.85
     enshr
    -0.82
     harmonize
    -0.80
     disambigu
    -0.79
     reorganized
    -0.79
    POSITIVE LOGITS
     magis
    1.02
     monaster
    0.97
     seksi
    0.91
     nomine
    0.88
     trast
    0.87
     alpes
    0.86
     Politica
    0.85
     cæ
    0.81
     Trasp
    0.81
     sibi
    0.81
    Activations Density 2.233%

    No Known Activations