© 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. 840
    Prev
    Next
    INDEX
    Explanations

    financial figures and amounts in Indian Rupees (Rs)

    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
    1896
    +0.08
    0.3%
    50
    +0.08
    0.3%
    1141
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1896
    +0.08
    0.03
    1343
    +0.08
    0.04
    690
    +0.07
    0.04
    Negative Logits
    <bos>
    -1.14
    
    -0.63
     reunite
    -0.62
     put
    -0.62
    addGroup
    -0.61
    define
    -0.61
     be
    -0.60
     establish
    -0.59
     see
    -0.58
     give
    -0.58
    POSITIVE LOGITS
     maroc
    1.34
     meis
    1.32
     wien
    1.31
     napoli
    1.31
     lidl
    1.31
     effe
    1.30
     véhic
    1.30
     applau
    1.28
     incess
    1.26
     milano
    1.25
    Activations Density 0.341%

    No Known Activations