© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 82
    Prev
    Next
    INDEX
    Explanations

    references to technical terms and company names

    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
    50
    +0.12
    0.5%
    1978
    +0.07
    0.3%
    344
    +0.06
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.12
    0.06
    1343
    +0.07
    0.07
    344
    +0.06
    0.05
    Negative Logits
    <bos>
    -1.59
    ransition
    -0.82
    ตร์
    -0.74
     ensure
    -0.73
    public
    -0.69
    ///**
    -0.69
    define
    -0.69
    ുള്ള
    -0.68
                
    -0.68
            
    -0.68
    POSITIVE LOGITS
     affor
    2.43
     increa
    2.23
     volunte
    2.13
     guarante
    2.10
     véhic
    2.07
     philanth
    2.06
     maneu
    2.04
     inev
    2.02
     Intere
    2.01
     Confu
    2.00
    Activations Density 0.242%

    No Known Activations