© 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
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 462
    Prev
    Next
    INDEX
    Explanations

    mentions of locations, especially with political or official connotations

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    395
    +0.09
    0.3%
    1036
    +0.09
    0.3%
    1492
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.09
    0.06
    690
    +0.09
    0.05
    283
    +0.08
    0.01
    Negative Logits
     længere
    -0.59
     heapq
    -0.57
    người
    -0.55
    những
    -0.55
     gik
    -0.54
    acteria
    -0.53
     grass
    -0.53
     tæt
    -0.53
     aDecoder
    -0.52
    ädigung
    -0.52
    POSITIVE LOGITS
    lu
    1.80
     Chrome
    1.09
    Chrome
    1.07
     chrome
    1.05
    LU
    1.04
    luk
    1.01
     Luc
    1.00
     chrom
    0.98
    Luc
    0.92
    lug
    0.90
    Activations Density 0.320%

    No Known Activations