© 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. 0-RES-JB
    11. 2142
    Prev
    Next
    INDEX
    Explanations

    terms related to virtual machines (VMs) and virtualization technology

    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
    871
    +0.13
    0.4%
    1778
    +0.11
    0.4%
    1052
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1778
    +0.13
    0.04
    871
    +0.11
    0.04
    1343
    +0.10
    0.06
    Negative Logits
    <bos>
    -1.12
    <?
    -0.62
    /**
    -0.60
    Referencie
    -0.60
     pripra
    -0.59
    monių
    -0.58
     pogod
    -0.58
     lju
    -0.58
    ⓧ
    -0.57
     ljud
    -0.57
    POSITIVE LOGITS
     Vaugh
    1.69
     affor
    1.69
     increa
    1.61
     VD
    1.59
     volunte
    1.55
     Juf
    1.52
     strick
    1.48
     stockholm
    1.46
     reluct
    1.45
     impra
    1.45
    Activations Density 0.232%

    No Known Activations