© 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. 3425
    Prev
    Next
    INDEX
    Explanations

    information related to public health, insurance, policy changes, and geographical concerns

    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
    50
    +0.25
    1.0%
    897
    +0.13
    0.5%
    1577
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.25
    0.11
    204
    +0.13
    0.07
    1137
    +0.11
    0.10
    Negative Logits
    <bos>
    -1.33
    RT
    -0.82
     Mit
    -0.82
    Mit
    -0.80
    CP
    -0.79
     par
    -0.77
    Py
    -0.75
    Por
    -0.74
    PP
    -0.74
    Conv
    -0.74
    POSITIVE LOGITS
     maneu
    2.73
     increa
    2.73
     impra
    2.72
     unce
    2.66
     reluct
    2.65
     squa
    2.64
     unden
    2.63
     fta
    2.60
     ftu
    2.59
     inev
    2.59
    Activations Density 1.853%

    No Known Activations