© 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. 6-RES-JB
    11. 5723
    Prev
    Next
    INDEX
    Explanations

    mentions of internet security technologies and related features

    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
    +0.24
    0.9%
    752
    +0.08
    0.3%
    939
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1284
    +0.24
    0.04
    485
    +0.08
    0.03
    500
    +0.07
    0.03
    Negative Logits
    <bos>
    -3.39
    ⓧ
    -0.82
    /***
    -0.81
    })();
    -0.72
    djangoproject
    -0.66
    /*!
    -0.65
    Portale
    -0.63
    //}
    -0.63
    endwhile
    -0.61
    //---
    -0.60
    POSITIVE LOGITS
     santiago
    1.44
     bandung
    1.39
     javier
    1.34
     frankfurt
    1.32
     munich
    1.31
     stockholm
    1.31
     fernando
    1.27
     napoli
    1.26
     alberto
    1.26
     vectorial
    1.26
    Activations Density 0.228%

    No Known Activations