© 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. 4092
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical concepts, particularly slopes and intercepts

    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
    341
    +0.16
    0.8%
    437
    +0.15
    0.7%
    559
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    437
    +0.16
    0.02
    1805
    +0.15
    0.02
    1376
    +0.13
    0.02
    Negative Logits
    <bos>
    -0.99
    rungsseite
    -0.78
     Newberry
    -0.70
     كومونز
    -0.64
    
    
    -0.61
    StoreMessageInfo
    -0.58
     Yarmouth
    -0.58
    UrlResolution
    -0.57
     Hereford
    -0.54
    <?
    -0.53
    POSITIVE LOGITS
     slope
    1.19
    slope
    1.18
     slopes
    1.08
     Slope
    1.04
    Slope
    1.00
     steep
    0.93
     magis
    0.92
     quæ
    0.88
     ibi
    0.86
    slo
    0.84
    Activations Density 0.147%

    No Known Activations