© 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. 7629
    Prev
    Next
    INDEX
    Explanations

    technical terms related to specific institutions, research fields, and publications

    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
    +0.12
    0.5%
    1871
    +0.10
    0.4%
    814
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.12
    0.10
    283
    +0.10
    0.01
    304
    +0.10
    -0.02
    Negative Logits
    <bos>
    -2.39
    ⓧ
    -0.84
     touch
    -0.67
     awakeFromNib
    -0.65
     astore
    -0.64
     ser
    -0.64
     call
    -0.63
     can
    -0.63
    <?
    -0.63
     relax
    -0.62
    POSITIVE LOGITS
     lele
    1.75
     Præ
    1.74
     seksi
    1.72
     silikon
    1.71
     maksi
    1.70
     karton
    1.70
     Græ
    1.68
     kasa
    1.68
     kaos
    1.68
     antik
    1.66
    Activations Density 1.141%

    No Known Activations