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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 247
    Prev
    Next
    INDEX
    Explanations

    locations and names of people who have passed away in obituary-type texts

    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
    1520
    +0.11
    0.5%
    1140
    +0.11
    0.4%
    506
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    648
    +0.11
    0.07
    609
    +0.11
    0.06
    227
    +0.10
    0.07
    Negative Logits
    <bos>
    -1.59
    ⓧ
    -0.62
    //});
    -0.55
    <?
    -0.55
    ///**
    -0.54
     ORGANISM
    -0.54
    ernoo
    -0.54
    WireFormatLite
    -0.53
    EndProject
    -0.53
    IsMutable
    -0.53
    POSITIVE LOGITS
     maksi
    1.19
     kasa
    1.18
     saar
    1.12
     véhic
    1.11
     panik
    1.09
     Minang
    1.06
     stockholm
    1.05
     étrang
    1.04
     Dica
    1.01
     confé
    1.01
    Activations Density 0.537%

    No Known Activations