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. 6878
    Prev
    Next
    INDEX
    Explanations

    locations or landmarks related to a region or city

    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
    +0.10
    0.4%
    1041
    +0.09
    0.3%
    1741
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.10
    0.10
    648
    +0.09
    0.09
    1013
    +0.08
    0.09
    Negative Logits
    <bos>
    -2.50
    portál
    -0.99
    HasIndex
    -0.88
    IsRequired
    -0.87
    Rptr
    -0.85
    FlatAppearance
    -0.82
    RTDA
    -0.81
    െ
    -0.80
    alignSelf
    -0.79
    HasColumnType
    -0.77
    POSITIVE LOGITS
     maneu
    2.50
     increa
    2.48
     affor
    2.35
     depic
    2.35
     milf
    2.34
     excru
    2.31
     Juf
    2.31
     accla
    2.29
     inev
    2.28
     aen
    2.25
    Activations Density 0.553%

    No Known Activations