© 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. 102
    Prev
    Next
    INDEX
    Explanations

    expressions related to physical locations or towns

    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
    1350
    +0.08
    0.2%
    33
    +0.07
    0.2%
    789
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.08
    0.01
    1343
    +0.07
    0.04
    1363
    +0.06
    0.03
    Negative Logits
     ineffec
    -0.66
     introduce
    -0.62
     Jamieson
    -0.60
     later
    -0.59
     fatally
    -0.59
     Adair
    -0.58
     unjustly
    -0.58
     preferentially
    -0.57
     retracted
    -0.57
     wrongfully
    -0.57
    POSITIVE LOGITS
    wn
    1.89
    own
    1.50
    owns
    1.31
    awn
    1.21
    OWN
    1.15
    WN
    1.12
     meis
    1.11
     applau
    1.08
     bourgeo
    1.08
     fatis
    1.07
    Activations Density 0.300%

    No Known Activations