© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 6610
    Prev
    Next
    INDEX
    Explanations

    mentions of food-related entities such as restaurants and cookbooks

    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
    1604
    +0.15
    0.6%
    990
    +0.14
    0.6%
    1145
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.15
    0.07
    783
    +0.14
    0.05
    990
    +0.13
    0.05
    Negative Logits
     Mère
    -1.84
     Septembre
    -1.70
     Souha
    -1.68
     Sén
    -1.64
     Venise
    -1.60
     Aéroport
    -1.59
     Juillet
    -1.58
     Octobre
    -1.54
     Membre
    -1.54
     paillettes
    -1.52
    POSITIVE LOGITS
     friable
    1.35
     ferru
    1.12
     roth
    1.07
     suscep
    1.07
     moore
    1.07
     uncin
    1.05
     manchester
    1.03
     douglas
    1.03
     unce
    1.01
     effe
    1.01
    Activations Density 0.501%

    No Known Activations