Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 14792
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    674
    +0.21
    0.7%
    1253
    +0.08
    0.3%
    1622
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    -0.21
    0.00
    0
    -0.08
    0.00
    1
    -0.06
    0.00
    Negative Logits
     reluct
    -6.02
     shenan
    -5.85
     impra
    -5.74
     unspeak
    -5.65
     disagre
    -5.65
     increa
    -5.59
     encomp
    -5.47
     depic
    -5.42
     indestru
    -5.36
     maneu
    -5.29
    POSITIVE LOGITS
    <bos>
    7.93
     Walkover
    2.40
     Paglinawan
    2.20
    expandindo
    2.10
    GEBURTSDATUM
    2.09
    Personendaten
    1.98
     Himo
    1.95
    脚注の使い方
    1.94
    Panamoan
    1.94
     himo
    1.92
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.