© 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. 13714
    Prev
    Next
    INDEX
    Explanations

    terms related to debates, viewpoints, and claims

    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
    198
    +0.16
    0.5%
    872
    +0.13
    0.4%
    791
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.16
    0.07
    791
    +0.13
    0.05
    963
    +0.09
    0.05
    Negative Logits
     murano
    -0.94
     tupperware
    -0.93
     affor
    -0.92
     indestru
    -0.91
     oreo
    -0.91
     cushi
    -0.90
     snoopy
    -0.90
     strick
    -0.89
     nutella
    -0.88
     eiffel
    -0.86
    POSITIVE LOGITS
    Argumento
    0.68
     claims
    0.64
     argument
    0.63
     often
    0.62
     arguments
    0.60
    argument
    0.60
     claimed
    0.60
     claim
    0.60
     discussions
    0.60
     injus
    0.59
    Activations Density 0.660%

    No Known Activations