© 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. 426
    Prev
    Next
    INDEX
    Explanations

    the word "all" at a high activation level

    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
    50
    +0.14
    0.6%
    1296
    +0.06
    0.2%
    1265
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    710
    +0.14
    0.03
    1696
    +0.06
    0.02
    1546
    +0.05
    0.02
    Negative Logits
    <bos>
    -2.26
    /***
    
    -0.72
    <tfoot>
    -0.72
    ⓧ
    -0.71
    public
    -0.62
    ///**
    -0.59
    <?
    
    -0.58
    {{--
    -0.58
     springfox
    -0.58
    //
    -0.58
    POSITIVE LOGITS
     stockholm
    1.37
     maneu
    1.32
     maroc
    1.30
     lidl
    1.29
     meis
    1.25
     fortn
    1.24
     catég
    1.23
     cartier
    1.23
     lele
    1.22
     Juf
    1.22
    Activations Density 0.131%

    No Known Activations