© 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. 367
    Prev
    Next
    INDEX
    Explanations

    technical terms related to safety and compliance in hazardous locations

    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
    +0.30
    1.2%
    1150
    +0.12
    0.5%
    297
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    924
    +0.30
    0.12
    336
    +0.12
    0.08
    678
    +0.09
    0.10
    Negative Logits
    <bos>
    -2.99
    ⓧ
    -1.07
    /**
    -1.02
    <?
    -0.99
    
    -0.90
    /*
    -0.82
    HasIndex
    -0.74
    /*++
    -0.72
    Transcripción
    -0.72
     became
    -0.65
    POSITIVE LOGITS
     maroc
    1.61
     maneu
    1.55
     milano
    1.42
     impra
    1.38
     increa
    1.35
     napoli
    1.35
     stockholm
    1.34
     exorbit
    1.34
     bandung
    1.33
     impractica
    1.31
    Activations Density 2.527%

    No Known Activations