© 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. 618
    Prev
    Next
    INDEX
    Explanations

    keywords related to venture capital and business events

    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
    545
    +0.11
    0.3%
    58
    +0.10
    0.3%
    489
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.11
    0.06
    283
    +0.10
    0.02
    1120
    +0.09
    0.05
    Negative Logits
     hasbro
    -0.73
     barbarous
    -0.73
     friable
    -0.71
     unspeak
    -0.69
     Ciò
    -0.68
     🤣🤣
    -0.66
     biofilm
    -0.66
     împre
    -0.65
     toată
    -0.65
     gtx
    -0.64
    POSITIVE LOGITS
     Kr
    1.46
    VC
    1.42
    Kr
    1.28
     VC
    1.18
    kr
    1.16
    vc
    1.07
     vc
    1.06
     Vc
    1.05
     kr
    1.05
     Kategor
    1.02
    Activations Density 0.369%

    No Known Activations