© 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. 989
    Prev
    Next
    INDEX
    Explanations

    the word "also" in 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.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
    0.5%
    1241
    +0.06
    0.2%
    707
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    172
    +0.14
    0.04
    1241
    +0.06
    0.03
    74
    +0.05
    0.04
    Negative Logits
    <bos>
    -1.69
    /***
    -1.03
     intersper
    -0.91
     endow
    -0.74
     enshr
    -0.74
    <?
    -0.73
     Mlle
    -0.70
     disbur
    -0.69
     disarm
    -0.69
     banish
    -0.68
    POSITIVE LOGITS
    inderella
    0.79
     chrysler
    0.76
     bloss
    0.71
     particolar
    0.69
     brune
    0.67
     cabrio
    0.65
     vulné
    0.64
     depoz
    0.63
    NUMX
    0.63
     vry
    0.63
    Activations Density 0.151%

    No Known Activations