© 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. 6-RES-JB
    11. 6978
    Prev
    Next
    INDEX
    Explanations

    sentence structures and instructions sequential to perform a specific task

    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
    +0.25
    1.0%
    1385
    +0.15
    0.6%
    297
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.25
    0.11
    1478
    +0.15
    0.06
    297
    +0.12
    0.07
    Negative Logits
    <bos>
    -2.60
     intersper
    -1.20
    ⓧ
    -1.16
    <?
    -1.00
     Mlle
    -0.99
     endow
    -0.99
    
    -0.99
    /**
    -0.97
     encomp
    -0.94
     forbear
    -0.93
    POSITIVE LOGITS
    '__
    0.56
     maroc
    0.54
     divertidos
    0.52
     CGRect
    0.50
     jawa
    0.50
    ]!='
    0.49
     sheet
    0.49
     OBJET
    0.49
    gruntled
    0.49
     sheets
    0.47
    Activations Density 0.737%

    No Known Activations