© 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. 14204
    Prev
    Next
    INDEX
    Explanations

    phrases related to human rights violations and socio-political issues

    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
    674
    +0.11
    0.3%
    604
    +0.09
    0.3%
    1284
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1288
    +0.11
    0.06
    1262
    +0.09
    0.05
    584
    +0.07
    0.05
    Negative Logits
     lele
    -0.87
     „,
    -0.80
     reft
    -0.79
     labd
    -0.79
     seiz
    -0.78
     reluct
    -0.78
     indestru
    -0.77
     disagre
    -0.77
     idr
    -0.77
     tranf
    -0.77
    POSITIVE LOGITS
    ghijklmnop
    0.56
    cuerdo
    0.51
    Inoltre
    0.50
    Conclusiones
    0.50
    Ottimo
    0.50
    Tecnología
    0.49
     acred
    0.49
     impide
    0.49
    chehen
    0.48
     Siamo
    0.48
    Activations Density 0.264%

    No Known Activations