© 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. 8335
    Prev
    Next
    INDEX
    Explanations

    plural nouns ending with 'ness'

    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
    577
    +0.14
    0.6%
    1892
    +0.11
    0.5%
    228
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.14
    0.08
    1871
    +0.11
    0.03
    1343
    +0.11
    0.08
    Negative Logits
    <bos>
    -1.21
     monitor
    -0.74
     select
    -0.65
    дкой
    -0.61
    contentLoaded
    -0.57
     Sunday
    -0.57
     hit
    -0.57
     prior
    -0.56
     distributed
    -0.56
     home
    -0.56
    POSITIVE LOGITS
     unwarran
    1.60
     ecru
    1.54
     impra
    1.53
     impractica
    1.52
     pamph
    1.50
     philanth
    1.48
     unlaw
    1.48
     indestru
    1.47
     encomp
    1.46
     affor
    1.44
    Activations Density 0.884%

    No Known Activations