© 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
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 1121
    Prev
    Next
    INDEX
    Explanations

    phrases related to people and their personal details, such as names, locations, and occupations

    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
    900
    +0.10
    0.3%
    1056
    +0.08
    0.2%
    200
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.10
    0.02
    1056
    +0.08
    0.02
    150
    +0.07
    0.02
    Negative Logits
    <bos>
    -0.91
     hjæl
    -0.78
     taget
    -0.78
     brugt
    -0.67
     jaya
    -0.66
     lanka
    -0.66
     længere
    -0.63
     tager
    -0.63
     køb
    -0.63
     tæn
    -0.63
    POSITIVE LOGITS
     Ind
    2.60
    ind
    2.50
    Ind
    2.44
     ind
    2.25
     IND
    2.18
    IND
    2.14
     Inde
    1.52
    indi
    1.45
    inds
    1.41
     Indi
    1.36
    Activations Density 0.136%

    No Known Activations