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. 74
    Prev
    Next
    INDEX
    Explanations

    technical terms related to engineering, technology, and internet concepts, as well as meta tags

    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
    32
    +0.22
    1.0%
    555
    +0.15
    0.7%
    506
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    32
    +0.22
    0.03
    1896
    +0.15
    0.02
    568
    +0.12
    0.02
    Negative Logits
    <bos>
    -1.31
     ***!
    -0.67
    addCriterion
    -0.64
    uxxxx
    -0.52
    RTSN
    -0.52
    Havolalar
    -0.52
    andaag
    -0.51
    Carcinogenicity
    -0.51
    keyColumn
    -0.50
     Савезне
    -0.50
    POSITIVE LOGITS
     Meta
    1.61
     meta
    1.53
    Meta
    1.44
    meta
    1.39
     méta
    1.36
     META
    1.32
     metast
    1.18
     metadata
    1.16
     Metadata
    1.15
     metas
    1.04
    Activations Density 0.252%

    No Known Activations