© 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. 85
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and products

    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
    101
    +0.09
    0.3%
    1937
    +0.08
    0.3%
    241
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.09
    0.04
    783
    +0.08
    0.03
    823
    +0.08
    0.03
    Negative Logits
    <bos>
    -1.05
     relocate
    -0.68
     put
    -0.66
     defray
    -0.63
     reimburse
    -0.61
    public
    -0.61
     abolish
    -0.60
     cancel
    -0.59
     prioritize
    -0.59
     expel
    -0.59
    POSITIVE LOGITS
     applau
    1.32
     multicolore
    1.18
     roul
    1.15
     rafra
    1.15
     matel
    1.15
     bourgeo
    1.14
     sappi
    1.13
     😭😭
    1.12
     !...
    1.11
     casio
    1.11
    Activations Density 0.282%

    No Known Activations