© 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. 79
    Prev
    Next
    INDEX
    Explanations

    references to security measures and return policies in online stores

    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
    1548
    +0.10
    0.3%
    1491
    +0.09
    0.3%
    228
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.10
    0.05
    1343
    +0.09
    0.04
    1120
    +0.07
    0.04
    Negative Logits
     Minang
    -1.09
     disagre
    -1.08
     withal
    -1.01
     kani
    -0.97
     quitted
    -0.94
     vainly
    -0.94
     bandung
    -0.94
     lola
    -0.93
     tolerably
    -0.88
     apprehen
    -0.87
    POSITIVE LOGITS
    Sung
    2.06
    sung
    2.01
     Sung
    2.00
     sung
    1.87
     sunglasses
    1.15
     Sunglasses
    1.05
    SUNG
    0.94
    alnız
    0.82
     Platinum
    0.76
    Platinum
    0.72
    Activations Density 0.333%

    No Known Activations