© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 4018
    Prev
    Next
    INDEX
    Explanations

    mentions of specific medication names and dosages

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    260
    +0.09
    0.3%
    50
    +0.07
    0.3%
    678
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.09
    0.11
    678
    +0.07
    0.10
    1927
    +0.07
    0.07
    Negative Logits
    <bos>
    -2.40
     AssemblyCompany
    -0.67
    <?
    -0.65
    /**
    -0.63
    Географи
    -0.62
    
    -0.61
    ⓧ
    -0.60
    habited
    -0.58
    χεία
    -0.58
    ngOnDestroy
    -0.58
    POSITIVE LOGITS
     silikon
    1.51
     kram
    1.46
     karton
    1.43
     kosme
    1.36
     seksi
    1.35
     keramik
    1.34
     alkoh
    1.32
     kafe
    1.30
     Strukt
    1.29
     panik
    1.27
    Activations Density 1.852%

    No Known Activations