© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 2548
    Prev
    Next
    INDEX
    Explanations

    phrases related to gerrymandering and technical instructions or code snippets

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1038
    +0.10
    0.3%
    416
    +0.10
    0.3%
    453
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.10
    0.06
    466
    +0.10
    0.05
    850
    +0.10
    0.04
    Negative Logits
    Билгалдахарш
    -0.56
    <bos>
    -0.52
     Utilize
    -0.46
    hänge
    -0.44
    gabriel
    -0.44
     Sia
    -0.43
    abestanden
    -0.43
    cupcake
    -0.43
    rbp
    -0.43
    Inggris
    -0.42
    POSITIVE LOGITS
     kafe
    1.01
     silikon
    0.96
     lele
    0.93
     maksi
    0.92
     bandung
    0.91
     traktor
    0.91
     teras
    0.90
     ekos
    0.88
     surabaya
    0.88
     lemp
    0.88
    Activations Density 0.284%

    No Known Activations