© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 6307
    Prev
    Next
    INDEX
    Explanations

    descriptions related to laboratory techniques and equipment

    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
    +0.21
    0.9%
    876
    +0.20
    0.9%
    1013
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.21
    0.02
    876
    +0.20
    -0.01
    1499
    +0.13
    0.07
    Negative Logits
    <bos>
    -3.41
    ⓧ
    -0.90
    <tfoot>
    -0.88
    rungsseite
    -0.84
    TargetException
    -0.80
    BeginInit
    -0.80
    ɵɵelementEnd
    -0.78
    COMO
    -0.77
    styleType
    -0.75
    usercontent
    -0.75
    POSITIVE LOGITS
     aen
    2.69
     effe
    2.65
     thut
    2.60
     increa
    2.50
     ftu
    2.49
     fta
    2.44
     inev
    2.41
     maneu
    2.40
     fte
    2.37
     fup
    2.36
    Activations Density 0.636%

    No Known Activations