© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 565
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software usage and implementation

    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
    381
    +0.11
    0.4%
    1618
    +0.09
    0.3%
    752
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.11
    0.06
    511
    +0.09
    0.04
    344
    +0.08
    0.04
    Negative Logits
     serce
    -1.07
     święta
    -1.00
     tæn
    -0.91
     mieszkań
    -0.90
     fiatal
    -0.89
     férfi
    -0.88
     női
    -0.87
     gyerek
    -0.85
     szép
    -0.85
     urodz
    -0.84
    POSITIVE LOGITS
     ftu
    2.03
     fta
    1.99
     vns
    1.94
     fup
    1.93
     fep
    1.92
     inev
    1.90
     maksi
    1.87
     purcha
    1.86
     effe
    1.83
     affor
    1.82
    Activations Density 0.162%

    No Known Activations