© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 647
    Prev
    Next
    INDEX
    Explanations

    mentions of the company Amazon

    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
    699
    +0.10
    0.3%
    1896
    +0.10
    0.3%
    101
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    501
    +0.10
    0.03
    1896
    +0.10
    0.02
    1120
    +0.09
    0.03
    Negative Logits
    /*
    -0.73
    /**
    -0.70
    <bos>
    -0.65
    /*++
    -0.57
    <?
    -0.57
    </tbody>
    -0.56
     springfox
    -0.55
    fektions
    -0.52
    enumerate
    -0.51
    ുറ
    -0.51
    POSITIVE LOGITS
     maneu
    1.09
     AMAZON
    1.07
     amazon
    1.05
     Amazon
    1.05
    Amazon
    1.03
     stockholm
    0.98
     malheure
    0.96
     habile
    0.96
     accla
    0.95
     véhic
    0.95
    Activations Density 0.316%

    No Known Activations