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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 281
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and concepts related to territoriality, formation of images, and theoretical questions in a philosophical context

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.18
    0.8%
    872
    +0.14
    0.6%
    304
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    872
    +0.18
    0.13
    2006
    +0.14
    0.08
    509
    +0.10
    0.05
    Negative Logits
    <bos>
    -3.29
    /*!
    -0.65
    MemoryWarning
    -0.63
     thu
    -0.63
    /***
    -0.62
    
    -0.62
    <?
    -0.61
     proved
    -0.60
    #![
    -0.59
    /*++
    -0.59
    POSITIVE LOGITS
     napoli
    1.72
     milano
    1.62
     affor
    1.59
     bandung
    1.58
     increa
    1.56
     maroc
    1.55
     effe
    1.51
     wien
    1.50
     fatis
    1.49
     santiago
    1.49
    Activations Density 2.245%

    No Known Activations