© 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. 3716
    Prev
    Next
    INDEX
    Explanations

    names of journalists

    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
    764
    +0.28
    1.0%
    1343
    +0.21
    0.7%
    599
    +0.19
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.28
    0.08
    137
    +0.21
    0.07
    1343
    +0.19
    0.06
    Negative Logits
    SourceChecksum
    -0.61
     Wikimédia
    -0.59
    InstrumentedTest
    -0.57
    RTLD
    -0.55
    <bos>
    -0.55
    Viitteet
    -0.54
    NOPQRST
    -0.53
    fjspx
    -0.52
    contentLoaded
    -0.52
    fromnode
    -0.52
    POSITIVE LOGITS
     shenan
    0.96
     intersper
    0.95
     unspeak
    0.94
     hairc
    0.89
     maneu
    0.89
     philanth
    0.87
     encomp
    0.87
     Incenti
    0.85
     affor
    0.84
     indestru
    0.84
    Activations Density 0.618%

    No Known Activations