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. 76
    Prev
    Next
    INDEX
    Explanations

    hardware specifications related to storage capacity

    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
    +0.21
    0.8%
    1385
    +0.11
    0.4%
    781
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    190
    +0.21
    0.04
    1385
    +0.11
    0.04
    781
    +0.10
    0.04
    Negative Logits
    <bos>
    -3.03
    ⓧ
    -0.67
    setClass
    -0.64
     relax
    -0.63
    MergeFrom
    -0.62
    FunctionFlags
    -0.62
    tagext
    -0.62
    rungsseite
    -0.62
    AnchorStyles
    -0.60
    MessageOf
    -0.60
    POSITIVE LOGITS
     ecru
    1.42
     swarovski
    1.39
     santiago
    1.36
     rodriguez
    1.34
     bandung
    1.33
     napoli
    1.29
     alberto
    1.27
     milano
    1.27
     maneu
    1.26
     gmbh
    1.25
    Activations Density 0.202%

    No Known Activations