© 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. 4367
    Prev
    Next
    INDEX
    Explanations

    discussion of structured processes and methods

    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
    +0.29
    1.0%
    872
    +0.11
    0.4%
    1904
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    872
    +0.29
    0.07
    1904
    +0.11
    0.04
    1095
    +0.10
    0.04
    Negative Logits
    <bos>
    -1.85
     intersper
    -1.27
     encomp
    -1.13
     disambigu
    -0.94
     endow
    -0.93
     interposed
    -0.90
     endeavored
    -0.86
     vainly
    -0.86
     depic
    -0.85
     infinites
    -0.85
    POSITIVE LOGITS
     palio
    1.04
     sement
    0.95
     ferie
    0.93
     cajones
    0.93
     pompa
    0.92
     maroc
    0.89
     loto
    0.89
     bandung
    0.88
     divertimento
    0.86
     palab
    0.84
    Activations Density 0.705%

    No Known Activations