© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 733
    Prev
    Next
    INDEX
    Explanations

    names of a particular person, "Bem"

    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
    1994
    +0.14
    0.4%
    1464
    +0.10
    0.3%
    313
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.14
    0.05
    1363
    +0.10
    0.04
    690
    +0.10
    0.05
    Negative Logits
    <?
    -0.58
    úncia
    -0.58
    Witam
    -0.56
     Excelente
    -0.52
    ⓧ
    -0.51
    はじめに
    -0.50
    JAKARTA
    -0.50
    erequisites
    -0.50
    CppCodeGen
    -0.50
     литров
    -0.50
    POSITIVE LOGITS
     Bem
    1.80
    Bem
    1.51
     bem
    1.19
     BEM
    1.11
     quoique
    1.03
     délib
    1.02
     sober
    1.01
     Sober
    1.01
     HEX
    0.99
     lidl
    0.94
    Activations Density 0.346%

    No Known Activations