© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 228
    Prev
    Next
    INDEX
    Explanations

    mentions of soy-based ingredients or 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.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
    481
    +0.14
    0.8%
    1472
    +0.14
    0.7%
    555
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    478
    +0.14
    0.02
    732
    +0.14
    0.02
    227
    +0.14
    0.06
    Negative Logits
    HasForeignKey
    -0.77
    <bos>
    -0.66
    //};
    -0.64
    /**
    -0.63
    },[])
    -0.63
    UnitTesting
    -0.62
    autoIncrement
    -0.62
    Continuar
    -0.58
    BeforeMethod
    -0.57
    ]=="
    -0.57
    POSITIVE LOGITS
     swarovski
    0.94
     maneu
    0.92
     Momb
    0.89
     crf
    0.87
     impra
    0.87
     McLaugh
    0.87
     Bartholo
    0.84
     Punj
    0.82
     reluct
    0.81
     Soy
    0.81
    Activations Density 0.612%

    No Known Activations