© 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. 1056
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific technical terms or codes

    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
    1757
    +0.14
    0.6%
    172
    +0.14
    0.6%
    680
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.14
    0.10
    227
    +0.14
    0.08
    1343
    +0.13
    0.07
    Negative Logits
     disreg
    -0.87
     indestru
    -0.84
     impra
    -0.83
     unspeak
    -0.80
     resear
    -0.80
     certitude
    -0.79
     Mmm
    -0.77
    brazilian
    -0.76
     unavoid
    -0.75
     unlaw
    -0.73
    POSITIVE LOGITS
    o
    0.73
    y
    0.71
     wikipagina
    0.69
     kuti
    0.68
    ειτουργ
    0.66
    脚注の使い方
    0.65
    a
    0.64
    e
    0.62
    i
    0.62
    betical
    0.62
    Activations Density 0.572%

    No Known Activations