© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 986
    Prev
    Next
    INDEX
    Explanations

    words related to inducing various states or conditions

    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
    1961
    +0.08
    0.3%
    390
    +0.08
    0.2%
    50
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1380
    +0.08
    0.03
    1896
    +0.08
    0.02
    1975
    +0.07
    0.02
    Negative Logits
    <bos>
    -1.05
    setViewName
    -0.56
     Richardson
    -0.55
     remplace
    -0.51
    displayquote
    -0.50
    ContentAlignment
    -0.49
     problemów
    -0.49
    <?
    
    -0.49
     then
    -0.48
     Governors
    -0.48
    POSITIVE LOGITS
     imparts
    1.15
     imparted
    1.04
     maroc
    1.04
     imparting
    1.02
     [''
    1.01
     elic
    0.98
     maneu
    0.98
     chrysler
    0.97
     impart
    0.96
     elicit
    0.96
    Activations Density 0.213%

    No Known Activations