© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 537
    Prev
    Next
    INDEX
    Explanations

    the surname "Kagan" or "Santorum"

    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
    1178
    +0.09
    0.3%
    1865
    +0.07
    0.2%
    1438
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.09
    0.02
    1343
    +0.07
    0.04
    184
    +0.07
    0.02
    Negative Logits
    <bos>
    -1.05
    RotationOrder
    -0.66
    EndInit
    -0.62
    PerformLayout
    -0.61
    Cyfarwyddwr
    -0.59
     buhay
    -0.57
     مرئيه
    -0.57
    fromnode
    -0.56
    UnusedPrivate
    -0.56
    uxxxx
    -0.55
    POSITIVE LOGITS
    agan
    2.23
     thut
    1.36
     fta
    1.32
     ftu
    1.28
    AGAN
    1.22
     idr
    1.19
     laft
    1.19
     aen
    1.18
     fup
    1.16
    orum
    1.16
    Activations Density 0.244%

    No Known Activations