© 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. 7682
    Prev
    Next
    INDEX
    Explanations

    information related to people's careers and accomplishments

    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
    382
    +0.19
    0.6%
    1535
    +0.18
    0.5%
    2034
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.19
    0.09
    195
    +0.18
    0.06
    1535
    +0.16
    0.06
    Negative Logits
     Darum
    -0.65
    おわりに
    -0.59
     Zwar
    -0.58
    Cześć
    -0.57
     FetchType
    -0.53
     airpods
    -0.52
     سكانية
    -0.50
     SDLK
    -0.49
     womit
    -0.49
    церт
    -0.49
    POSITIVE LOGITS
     Thereafter
    0.86
     Subsequently
    0.82
     Afterward
    0.72
     Afterwards
    0.72
     Subsequent
    0.71
     Kategor
    0.71
     Later
    0.68
     rempla
    0.67
     Liban
    0.67
     Mahomet
    0.66
    Activations Density 0.301%

    No Known Activations