© 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. 0-RES-JB
    11. 1968
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations, particularly in the state of Maine

    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.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
    1335
    +0.09
    0.3%
    528
    +0.09
    0.3%
    629
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.09
    0.03
    990
    +0.09
    0.02
    1547
    +0.08
    0.02
    Negative Logits
     disbur
    -0.79
     Wtf
    -0.73
     underval
    -0.71
     intersper
    -0.69
    <?
    -0.69
     stratigraph
    -0.64
     endeavored
    -0.63
    /**
    -0.63
     endow
    -0.63
     Lmao
    -0.61
    POSITIVE LOGITS
     Maine
    2.37
    Maine
    2.23
     maine
    1.37
    maine
    1.16
     Luglio
    0.80
    ME
    0.78
     Giugno
    0.78
     ME
    0.76
     lobster
    0.72
     Lobster
    0.69
    Activations Density 0.196%

    No Known Activations