© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 3456
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating rank or size

    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
    +0.22
    0.8%
    1921
    +0.10
    0.3%
    1233
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1260
    +0.22
    0.03
    191
    +0.10
    0.03
    1042
    +0.09
    0.03
    Negative Logits
    <bos>
    -1.72
     dè
    -0.80
    marginHorizontal
    -0.79
    /***
    
    -0.76
     kasarigan
    -0.75
    marginVertical
    -0.74
    paddingVertical
    -0.73
     adal
    -0.71
    RTEX
    -0.71
     Administrativna
    -0.70
    POSITIVE LOGITS
     affor
    1.53
     impra
    1.48
     maneu
    1.47
     reluct
    1.46
     philanth
    1.46
     increa
    1.44
     unlaw
    1.41
     impractica
    1.38
     indestru
    1.35
     sophistic
    1.34
    Activations Density 0.112%

    No Known Activations