© 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. 2266
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and economic systems

    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
    1343
    +0.13
    0.4%
    1445
    +0.12
    0.4%
    50
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.13
    0.03
    919
    +0.12
    0.01
    599
    +0.12
    0.04
    Negative Logits
     onAnimation
    -0.55
     fabricants
    -0.44
     banques
    -0.44
    umesc
    -0.43
    Saludos
    -0.42
     ролях
    -0.42
     femei
    -0.42
    enschein
    -0.41
     nonatomic
    -0.41
     propósitos
    -0.41
    POSITIVE LOGITS
     unlaw
    1.07
     pamph
    1.06
     Khart
    1.01
     philanth
    0.99
     Keny
    0.98
     unwarran
    0.97
     impractica
    0.95
     Abbé
    0.93
     Confu
    0.92
     Pamph
    0.91
    Activations Density 0.449%

    No Known Activations