© 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. 163
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations and numbers

    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
    +0.19
    0.8%
    1343
    +0.10
    0.4%
    2019
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.19
    0.12
    1699
    +0.10
    0.05
    755
    +0.08
    0.08
    Negative Logits
    <bos>
    -2.31
    SharedDtor
    -1.27
    uxxxx
    -1.12
    HideFlags
    -1.09
    /**
    -1.08
    Autoritní
    -1.07
     invokingState
    -1.06
    EndGlobalSection
    -1.06
    Personendaten
    -1.05
    Vidite
    -1.05
    POSITIVE LOGITS
     maneu
    2.64
     increa
    2.42
     impra
    2.41
     disagre
    2.39
     affor
    2.36
     inev
    2.34
     accla
    2.34
     depic
    2.32
     reluct
    2.32
     guarante
    2.27
    Activations Density 1.823%

    No Known Activations