© 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. 496
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to electronic devices, especially DVD players

    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
    1994
    +0.10
    0.3%
    1328
    +0.08
    0.3%
    1870
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.10
    0.06
    1120
    +0.08
    0.05
    1363
    +0.08
    0.04
    Negative Logits
    <bos>
    -1.70
     effe
    -1.58
     fta
    -1.58
     wien
    -1.57
     fte
    -1.53
     thut
    -1.52
     aen
    -1.51
     oner
    -1.49
     desir
    -1.46
     encomp
    -1.46
    POSITIVE LOGITS
    PAL
    0.88
     RAM
    0.87
     PAL
    0.83
    CAM
    0.82
    CAD
    0.78
     CAM
    0.77
    augh
    0.76
     ISP
    0.74
    Flor
    0.73
    RAM
    0.70
    Activations Density 0.349%

    No Known Activations