© 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. 6-RES-JB
    11. 4630
    Prev
    Next
    INDEX
    Explanations

    words related to gradual changes or processes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.18
    0.7%
    1379
    +0.12
    0.4%
    1777
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    318
    +0.18
    0.06
    2008
    +0.12
    0.03
    1193
    +0.09
    0.05
    Negative Logits
    <bos>
    -1.90
    <?
    -0.60
    
    -0.59
     harmonize
    -0.59
     inaugurate
    -0.58
     endow
    -0.58
     intersper
    -0.57
    ⓧ
    -0.57
     banish
    -0.56
     rejoin
    -0.56
    POSITIVE LOGITS
     maroc
    1.05
     blackpink
    1.03
     palio
    1.02
     grati
    1.01
     broderie
    1.00
     gradual
    1.00
     lele
    0.99
     tenerife
    0.99
     bandung
    0.98
     shopee
    0.98
    Activations Density 0.683%

    No Known Activations