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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 4782
    Prev
    Next
    INDEX
    Explanations

    terms related to academic discourse or scholarly debate

    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
    872
    +0.23
    1.1%
    1523
    +0.08
    0.4%
    50
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    872
    +0.23
    0.20
    1784
    +0.08
    0.12
    2015
    +0.08
    -0.02
    Negative Logits
    <bos>
    -3.16
    thâu
    -0.76
    InitStruct
    -0.66
    kháu
    -0.64
    Diwedd
    -0.63
     betweenstory
    -0.62
     enroll
    -0.61
     created
    -0.60
    <!--
    -0.60
     or
    -0.60
    POSITIVE LOGITS
     stockholm
    1.47
     jaya
    1.45
     maroc
    1.45
     milano
    1.43
     guarante
    1.42
     increa
    1.41
     wien
    1.41
     jacques
    1.40
     sappi
    1.40
     bandung
    1.40
    Activations Density 2.966%

    No Known Activations