© 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. 0-RES-JB
    11. 2474
    Prev
    Next
    INDEX
    Explanations

    mentions of specific items and prices

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    200
    +0.09
    0.3%
    1272
    +0.09
    0.3%
    1265
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    729
    +0.09
    0.03
    1265
    +0.09
    0.03
    1272
    +0.08
    0.02
    Negative Logits
    (".");
    -0.62
    (">>
    -0.61
    
    -0.61
    const
    -0.60
    <?
    -0.58
    ্
    -0.58
    ('.');
    -0.58
     נת
    -0.58
     continue
    -0.57
    )
    -0.57
    POSITIVE LOGITS
     ($
    1.93
     maneu
    1.61
     ($\
    1.60
     stockholm
    1.42
     squa
    1.41
     strick
    1.36
     fte
    1.35
     fto
    1.35
     wherea
    1.34
     affor
    1.34
    Activations Density 0.180%

    No Known Activations