Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 5456
    Prev
    Next
    INDEX
    Explanations

    contradictions or exceptions in the text

    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
    +0.17
    0.9%
    1950
    +0.16
    0.9%
    938
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1950
    +0.17
    0.06
    938
    +0.16
    0.04
    196
    +0.12
    0.04
    Negative Logits
    <bos>
    -3.09
    /***
    
    -0.76
    osoba
    -0.68
    ///**
    -0.65
    Пра
    -0.64
    //});
    -0.64
    {{--
    -0.64
    //}
    
    -0.62
    //};
    -0.61
    })();
    
    -0.61
    POSITIVE LOGITS
     ecru
    1.57
     lidl
    1.46
     affor
    1.46
     stockholm
    1.44
     bordeaux
    1.44
     peugeot
    1.43
     chrysler
    1.42
     maneu
    1.41
     frankfurt
    1.40
     saar
    1.40
    Activations Density 0.084%

    No Known Activations