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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5629
    Prev
    Next
    INDEX
    Explanations

    information related to technical details and specifications

    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
    +0.38
    1.8%
    1699
    +0.10
    0.5%
    382
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    921
    +0.38
    0.12
    776
    +0.10
    0.12
    1962
    +0.10
    0.11
    Negative Logits
    <bos>
    -2.46
    <?
    -0.81
    ⓧ
    -0.79
    ɵɵ
    -0.77
    /**
    -0.76
     springfox
    -0.76
    BUYER
    -0.74
    orElseThrow
    -0.71
    
    
    -0.70
    CreateMap
    -0.68
    POSITIVE LOGITS
     maneu
    2.59
     affor
    2.55
     accla
    2.54
     increa
    2.50
     reluct
    2.40
     inev
    2.35
     impra
    2.34
     emphat
    2.33
     resear
    2.26
     disagre
    2.25
    Activations Density 0.770%

    No Known Activations