© 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. 772
    Prev
    Next
    INDEX
    Explanations

    links or references to external websites

    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
    1323
    +0.07
    0.2%
    799
    +0.07
    0.2%
    327
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.07
    0.05
    1120
    +0.07
    0.05
    283
    +0.06
    0.01
    Negative Logits
    <bos>
    -1.11
     banish
    -0.80
     subdue
    -0.75
    ostruct
    -0.74
     deprive
    -0.73
     ratify
    -0.71
     rouse
    -0.71
     reinstate
    -0.70
     shuddered
    -0.69
     nourish
    -0.69
    POSITIVE LOGITS
     sergio
    1.30
     cristina
    1.28
     catég
    1.27
     alberto
    1.25
    Literat
    1.25
     felipe
    1.25
     jorge
    1.24
     javier
    1.22
     roberto
    1.21
     claudia
    1.20
    Activations Density 0.420%

    No Known Activations