© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 977
    Prev
    Next
    INDEX
    Explanations

    mention or information about specific locations

    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
    50
    +0.12
    0.4%
    1837
    +0.12
    0.4%
    410
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.12
    0.11
    283
    +0.12
    0.02
    1343
    +0.08
    0.08
    Negative Logits
    <bos>
    -2.63
     Städ
    -1.82
     Schloß
    -1.50
     Wiking
    -1.40
     Grafen
    -1.36
     Ufer
    -1.34
     Orgel
    -1.32
     Hafen
    -1.32
     Priester
    -1.31
     Fürst
    -1.30
    POSITIVE LOGITS
     increa
    2.84
     Juf
    2.81
     fta
    2.70
     affor
    2.69
     depic
    2.65
     impra
    2.65
     disagre
    2.63
     Confu
    2.63
     reluct
    2.60
     inev
    2.59
    Activations Density 0.907%

    No Known Activations