© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 788
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1034
    +0.08
    0.2%
    521
    +0.08
    0.2%
    492
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.08
    0.06
    283
    +0.08
    0.02
    690
    +0.08
    0.06
    Negative Logits
     himo
    -0.86
    portar
    -0.77
    теристика
    -0.72
    ViewFeatures
    -0.72
    DataAnnotations
    -0.71
     pollici
    -0.71
    genas
    -0.70
     <=",
    -0.70
    /**
    -0.68
    intios
    -0.66
    POSITIVE LOGITS
    cri
    1.37
     parch
    1.14
     unve
    1.10
     logarith
    1.10
     disreg
    1.09
     maneu
    1.04
     stratigraph
    1.04
     gaily
    1.04
     depic
    1.02
     ecru
    1.00
    Activations Density 0.417%

    No Known Activations